Supervertaler for memoQ: Docs for the memoQ plugin only # Supervertaler for memoQ Supervertaler for memoQ brings AI translation and your own terminology into **memoQ 11 and 12**, as two add-ins that work together. Unlike the Trados plugin, which docks its own panels into the editor, memoQ gives an add-in no window of its own. Supervertaler therefore works through memoQ’s existing surfaces – the machine-translation engine and the terminology pane – rather than adding new ones. In practice that turns out to suit it: the results appear exactly where you already look for them.  ### What it does **AI translation.** An LLM machine-translation engine using Anthropic, OpenAI or Google, with your own API key and your own instructions. It works segment by segment as you translate, and in bulk through **Pre-translate**. Inline tags survive the round trip. **It learns as you work.** Every segment you confirm is remembered, and the most relevant ones are shown to the model when it translates later segments in the same document. Settle on a term once and the rest of the document follows it – no configuration, no retraining, just your own approved choices fed forward. See [Self-learning translation](/memoq/self-learning/). **Your terminology, twice over.** Your Supervertaler termbases – shared with Supervertaler for Trados, or made in memoQ from scratch – appear as a memoQ terminology provider, matched terms highlighted in the source and entries listed in Translation results, *and* the ones you tick for it are sent to the model as required or forbidden terminology. Forbidden terms are enforced, not merely displayed. See [Terminology](/memoq/terminology/). **Translate with Claude Desktop or ChatGPT.** Connect an [AI assistant](/memoq/mcp-server/) with one button in the editor, and it reads the document you are translating, your confirmed segments and your termbases, and stages translations that flow into the grid when you press Pre-translate. Tokens are billed to your Claude or ChatGPT subscription rather than an API key, and every write into your document goes through your own hands. **A companion editor.** Translation instructions come from the same prompt library the Trados plugin uses, chosen and edited in the [Supervertaler editor](/memoq/prompt-editor/) – which is also where you pick the memory bank and termbases for a job, draft a prompt with AutoPrompt and watch what the plugin is doing. **One licence for both products.** The Supervertaler licence covers Supervertaler for Trados and Supervertaler for memoQ, with a 14-day free trial. See [Licensing](/memoq/licensing/). ### What it does not do memoQ does not let a plugin read its own term bases or translation memories, so terms defined in a memoQ term base are not visible to the AI. Supervertaler reads its own termbases instead, which it also displays alongside memoQ’s own term base hits. There is no chat panel and no document-wide search inside memoQ: a plugin can answer when asked for a translation, and that is all. The chat lives in Claude Desktop or ChatGPT; the prompt library lives in its own editor; and an assistant’s translations reach the grid only when you Pre-translate. [AI assistants → What it can and cannot do](/memoq/mcp-server/#what-it-can-and-cannot-do) has the full comparison with the Trados plugin. ### Where to start * [Installation](/memoq/installation/) – the installer, and switching it on in memoQ * [Getting started](/memoq/getting-started/) – a first translation * [Licensing](/memoq/licensing/) – the trial, and one licence for both products * [Terminology](/memoq/terminology/) – termbases, shared with Supervertaler for Trados * [AI assistants](/memoq/mcp-server/) – translating with Claude Desktop or ChatGPT * [The Supervertaler editor](/memoq/prompt-editor/) – prompts, memory banks, AutoPrompt and FigureLens # Context layers > The layers of context Supervertaler for memoQ puts in front of the AI, what each one adds, where memoQ lets it come from, and how to control them. A translation engine that sees only the sentence in front of it will translate that sentence well and the document badly. Supervertaler’s design is the opposite: every time memoQ asks it for a translation, it assembles a fresh snapshot of your work and hands the whole thing to the AI. That snapshot is built in **layers**. Some come from memoQ, some from your own recorded knowledge, and two of them come from parts of the document that no CAT tool normally shows you at all. They stack, and each one that is present removes a class of mistake the AI would otherwise make. This page is the single place that lists every layer. Supervertaler for Trados has [its own version of this page](/trados/context-layers/); the ideas are the same and the sources differ, because memoQ hands a plugin a different set of things. ## The layers | # | Layer | Where it comes from | Needs work from you | | -- | ------------------------------------ | --------------------------------------- | ------------------------ | | 1 | Project and job information | memoQ, with each request | no | | 2 | The segment being translated | memoQ | no | | 3 | Segments you have confirmed | your own confirmed rows | one setting, once | | 4 | The closest translation memory match | your TMs, routed by you | one setting, once | | 5 | Whether the row was rejected | memoQ | no | | 6 | Termbase terms and forbidden terms | your termbases | a termbase ticked AI | | 7 | SuperMemory memory banks | what you have recorded about the client | a bank per client | | 8 | List numbering | the original Word file | the live document link | | 9 | Figure descriptions | the images in your documents | two clicks in FigureLens | | 10 | The whole document | the live document link | for AutoPrompt only | ### 1. Project and job information The client, domain and subject recorded in memoQ’s project, the language pair, and which document the segment is in. memoQ sends these with every translation request, so they need no setting – but they are only as good as what the project manager filled in. An empty *Client* field in memoQ is an empty line in the prompt. **Toggle:** Translation settings → *Send surrounding segments and project metadata to the model*. ### 2. The segment being translated The source text, with its inline tags preserved so they can be put back in the right places. Always included; there is nothing to configure. ### 3. Segments you have confirmed Every segment you confirm is recorded, and the most lexically similar ones are shown to the model when it translates later segments of the same document. Confirm *electric module* once and the rest of the document follows. This is memoQ’s answer to a layer Trados gets for free. A Trados plugin is handed the segments surrounding the one it is translating; a memoQ MT plugin is not – memoQ reserves that channel for its own AGT engine – so Supervertaler builds the equivalent out of your confirmed work instead. It is arguably the better trade: every example is one you approved, rather than merely one that happens to be nearby. memoQ only sends confirmations to an engine selected under **Self-learning MT**, so that box must be ticked as well as the engine being chosen for translation. Until it is, nothing is captured and the [Activity window](/memoq/prompt-editor/#the-activity-window) says so. See [Self-learning](/memoq/self-learning/). **Toggle:** Translation settings → *Send surrounding segments and project metadata to the model*. ### 4. The closest translation memory match memoQ can forward the best fuzzy match for a segment to an MT engine, and when you route it to Supervertaler that match goes into the prompt ahead of everything else. From v0.1.8 it is offered as a **reference to check, not wording to follow**. A memory can hold translations made for other documents, products or clients, and they can be wrong. So the AI is told to check the match against the segment’s source and the document, reuse its wording only where it is correct for this segment, let the termbase and the document take precedence, and translate from the source when in doubt. A correct match is still reused; the AI just checks it first. Supervertaler for Trados treats its matches the same way. Set it in memoQ under **Edit machine translation settings → Send best fuzzy TM match to → Supervertaler**. It is deliberately *not* governed by the document-context toggle: a match you went out of your way to route here should not disappear because you turned off surrounding context. Two things to know about its shape. It is **one** match per segment – memoQ forwards the single best one, which is what its own setting says – rather than a set to choose among. And memoQ hands over the two segments without a match rate, so the prompt cannot tell the model *how* close the match is. Instead the segment’s own text is shown directly above the memory’s source, and the model is told to compare the two word by word, because a small difference can change the meaning. The match is forwarded for every segment memoQ asks about, batches included. ### 5. Whether the row was rejected memoQ tells the plugin each row’s translation state. When you have rejected a previous translation of a segment, the prompt says so and instructs the model to reconsider the terminology, structure and register rather than paraphrase what you refused. No setting; it simply happens on a row you marked rejected. ### 6. Termbase terms and forbidden terms Terms matched in the segment, with their approved renderings, and any terms marked forbidden. Forbidden terms are enforced rather than merely displayed. Worth being precise about the source, because the setting’s wording is optimistic: these come from **Supervertaler’s own termbases** – those ticked AI for the project in the [Termbases window](/memoq/terminology/#the-termbases-window) – not from memoQ’s term bases. memoQ passes term base hits to an MT plugin only through the rich lookup channel it reserves for its own engine, so a third-party plugin never receives them (memoQ has said a new endpoint will change that around the start of 2027). Your memoQ term bases still work normally in the grid; they just do not reach the model. [Termbase from this prompt’s terms](/memoq/prompt-editor/#termbase-from-this-prompts-terms) is the bridge: it turns a drafted prompt’s locked terms into the project termbase. While an AutoPrompt-drafted prompt is selected, its own locked-terms table is the authority and the termbases’ preferred renderings are held back – forbidden terms always travel. **Toggle:** Translation settings → *Send memoQ’s termbase hits and forbidden terms to the model*. ### 7. SuperMemory memory banks A bank of Markdown articles – `brief.md`, `terminology.md`, `style.md`, and any others you add – goes out with every request, up to about 32,000 tokens, and to AutoPrompt up to 40,000. Where a termbase gives the model flat pairs of terms, a memory bank gives it the **reasoning**: the decisions, the caveats, the client-specific overrides. The `_shared` bank travels alongside as house defaults. Banks are remembered per memoQ project, and a project you have never chosen one for uses none rather than inheriting the last – a bank carries one client’s terminology, and the wrong one is worse than none. See [Memory banks](/memoq/mcp-server/#memory-banks). **Shared by a team.** From v0.1.9, if your team shares its memory banks and prompts from a team folder, set up in Supervertaler for Trados (see [Sharing memory banks and prompts with a team folder](/trados/data-folder/#sharing-memory-banks-and-prompts-with-a-team-folder)), Supervertaler for memoQ uses it too. Memory banks and prompts come from the team folder; your licence, settings, API keys and termbases stay in your own data folder. memoQ has no setting of its own for it: it follows what is set in Supervertaler for Trados on the same computer. The team folder is checked when memoQ starts and when the editor starts. If it cannot be reached, your own memory banks and prompts are used until you restart, and you are told: the editor shows a warning when it opens, its **Settings** shows the team folder and whether it is in use, and the AI assistant’s list of memory banks says so too. If memoQ and the editor reached different folders – the network answered for one and not the other – the editor warns you, and restarting both puts them back on the same folder. ### 8. List numbering Word numbers claims, letters steps and bullets lists as paragraph properties, not as text, so memoQ’s grid never contains the `a)` or the `9.` and neither did anything the model received. Shown six unlettered steps and then *“steps a. to f.”*, a model will flag the reference as a possible defect in the source – a note that would have reached the client. Supervertaler reads the numbering out of the original `.docx`, counted over the whole document exactly as Word renders it, and sends each paragraph’s marker in front of its first segment as `[#e)]`, declared as structure to use and never to reproduce. Anything echoed back is stripped before it reaches the document. On by default, with no switch – but it needs the [live document link](/memoq/mcp-server/#the-live-document-link) connected, because that is what names the file memoQ imported. On a project checked out from a server that file is on the project manager’s machine, not yours; locate it once in [FigureLens](/memoq/prompt-editor/#where-the-documents-come-from) and the numbering is read from your copy. See [List numbering](/memoq/prompt-editor/#list-numbering-reaches-the-model-as-structure). ### 9. Figure descriptions The AI reads your text and cannot see your pictures. [**FigureLens**](/memoq/prompt-editor/#figurelens) closes that gap: it takes the images out of your documents into the memory bank’s `figures\` folder, shows each one to the AI together with what the document says about it, and saves a description – what it shows, which figure it is, which reference signs appear on it – as `figures.md` in the bank. From then on it rides along with layer 7 and is read with every request, so the model knows that the *valve (12)* in the sentence is the thing at the top right of Figure 3. Vector drawings – EMF and WMF, which is what a drawing placed from CAD usually is – are rendered to PNG on the way out, because no AI can read a metafile. Reference signs the model reads in a drawing that appear nowhere in the text are listed for you, because that is a defect worth raising with the client before filing. Two clicks per project, then it is automatic. One AI request per image; the panel says how many and to which provider before you click, and **Describe from the text only** is a free alternative that uses what the document itself says about each figure. ### 10. The whole document Not a translation layer: memoQ hands an MT plugin about ten segments at a time and never the document, so a per-segment prompt cannot contain it. What does get the whole document is [**AutoPrompt**](/memoq/prompt-editor/#autoprompt-drafting-a-prompt-for-the-open-project), which reads it through the live document link to classify the job and draft a prompt for it. That prompt then carries the document’s character into every subsequent request – which is the point: the document is read once, expensively, and its conclusions ride along cheaply thereafter. Where memoQ shows several files merged into one view, AutoPrompt offers **All N documents memoQ is showing** so the prompt is drafted from all of them rather than whichever file you happened to pick. ## What memoQ does not give a plugin Worth stating plainly, because the Trados page lists them and the difference is not a fault in either product: * **Surrounding segments.** memoQ passes neighbouring segments only through the rich lookup channel reserved for its own AGT engine. Layer 3 exists because of this. * **Term base hits.** The same channel, the same result. See layer 6. * **Attached files.** memoQ has no equivalent; there is nothing to attach a file to. None of these can be unlocked by a setting on your side. They are consequences of the plugin model, measured rather than assumed – and where one bites, the layer above it says what stands in for it. ## Stacking the layers The default composition – everything above except the ones that need a click – is a strong baseline and the one to start from. More context is not automatically better. The context window is finite, and a mature memory bank plus a large termbase ticked AI can push a prompt into the tens of thousands of tokens. The cost is smaller than it looks, because the stable half of every request is identical from batch to batch and is cached: on one 370-segment run, caching turned roughly $10 into roughly $4. But token count is not the only cost – three overlapping sources describing the same term can contradict each other, and the model then has to reconcile them on the fly. The layers that describe the **document** rather than the **client** – 5, 8 and 9 – are cheap, never contradict each other, and there is no case yet found where switching one off improved a translation. ## Seeing what is being sent The [Activity window](/memoq/prompt-editor/#the-activity-window) in the prompt editor logs every request with its token counts – regular, cached, written, output – so a layer that is not arriving shows up as a number that does not move. It also says, once per document, whether list numbering was available and why not when it was not, and which memory bank is in force. AutoPrompt’s **Preview context…** button shows exactly what would be sent before anything is sent, and makes no AI call. ## See also * [Prompt library and editor](/memoq/prompt-editor/) – AutoPrompt, FigureLens, list numbering, the settings * [Self-learning](/memoq/self-learning/) – how confirmed segments are captured and fed back * [Terminology](/memoq/terminology/) – the termbases the model reads * [MCP server and the live document link](/memoq/mcp-server/) – memory banks, and the channel layers 8 to 10 depend on * [Context layers in Supervertaler for Trados](/trados/context-layers/) – the same idea, a different host # Getting Started This walks through a first translation, assuming Supervertaler is [installed and switched on in memoQ](/memoq/installation/#switching-it-on-in-memoq). ### 1. Choose a provider and model Open **Supervertaler for memoQ** from the Start menu and choose **Settings → Translation settings…**. memoQ’s own dialog holds the same settings – **Configure plugin** on Supervertaler in an MT settings resource – and either place can change them; both read and write the same file. Fill in: | | | | ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Provider** | Anthropic, OpenAI or Google | | **Model** | a short list of the models worth recommending for that provider, with a line on each saying what it is for. **Fetch list** asks the provider for its full catalogue and **Show all models** adds it underneath – that is where to look for a model released after your copy of Supervertaler was built. The box also takes anything typed, for a gateway or a local model | | **API key** | your own key for that provider. All Supervertaler products share one key file at `C:\Users\\Supervertaler\settings\api-keys.json`, so a key you have already set in Supervertaler for Trados or Sidekick is picked up here and you can leave this empty – see [The Supervertaler editor](/memoq/prompt-editor/#api-keys-live-in-one-file) | | **Endpoint** | leave blank unless you are using a local model or a gateway | | **Segments per request** | how many segments go into one request during Pre-translate (memoQ hands the plugin about 10 at a time, so values above 10 make no difference) | | **Prompt** | a prompt from the shared library, or *(instructions below)* to type your own – see [The Supervertaler editor](/memoq/prompt-editor/). The editor chooses it from the panel at the top left | | **Pre-translate via Claude Desktop (MCP)** | leave **unticked** unless you translate through Claude Desktop or ChatGPT – see [AI assistants](/memoq/mcp-server/). Also the switch at the top right of the editor | In memoQ’s dialog, **Test connection** translates a short sentence for real, so it exercises the key, the model name and the endpoint together – a green result means everything works. ### 2. Turn on learning In memoQ, open the MT settings resource Supervertaler is ticked in – **Options → Default resources → MT settings**, or **Project home → Settings → MT settings** for a project you already have – and on its **Settings** tab set **Self-learning MT** to **Supervertaler**. This is what makes memoQ hand Supervertaler each segment as you confirm it. Without it the engine still translates, but it will not learn from your work. See [Self-learning translation](/memoq/self-learning/). Caution Changing this takes effect when memoQ next builds a translation engine. Restart memoQ after setting it. ### 3. Translate Open a document. With **Translation results** set to *Always*, landing on a segment fetches a translation automatically; it appears in the Translation results pane, labelled with the provider and model it came from. To translate in bulk, use **Preparation → Pre-translate** with *Use machine translation* enabled. ### 4. Confirm as you go Confirm segments as you normally would. Each confirmation is remembered, and later segments that resemble it are translated with your wording in front of the model. The effect is most visible on a document with recurring phrasing: settle a term in segment 3 and segment 40 will use it. ### Next * [Terminology](/memoq/terminology/) – termbases, including forbidden terms * [Self-learning translation](/memoq/self-learning/) – what is remembered, and for how long # Importing and exporting termbases Termbases live in Supervertaler’s shared database and are managed in the [Termbases window](/memoq/terminology/#the-termbases-window). This page is about the files that go in and out of it. ### What Import… and Add to… read Two shapes of file, and the difference is decided by looking at the file, not by you: **A delimited file with a header row** – what memoQ, Excel and Supervertaler for Trados export. Tab, semicolon or comma, whichever the header uses; cells may be quoted the way Excel quotes them. The two language columns are recognised by their headings – a language name such as *Dutch* or *English*, a code such as *nl* or *en-GB*, or a name with the code in brackets, *Dutch (nl)*. A column headed *Forbidden* (or *Status*) marks forbidden terms; one headed *Notes* (or *Definition*, *Comment*) is kept as the note. ```plaintext Dutch (nl) English (en) Forbidden Notes elektrische module electric module elektrische module electrical module forbidden koppelmechanisme coupling mechanism see claim 4 ``` **A Supervertaler glossary file** – the tab-separated format older versions of Supervertaler for memoQ used, and still what Export… writes when you ask for it. No header row; instead a `#` line naming the glossary and a `#!` line declaring its languages, then `source`, `target` and an optional third cell reading `forbidden`. ```plaintext # Client (case) v3 #! source=dut-NL target=eng-GB elektrische module electric module elektrische module electrical module forbidden ``` A file with neither a header row nor a `#!` line is taken to run the termbase’s own way round, and Add to… says so before writing. ### Direction A termbase is stored one way round – Dutch → English, say – and so is a file. When Add to… finds the file runs the other way from the termbase, each pair is turned as it is written, and the report afterwards says so. Import… takes the file’s own direction for the new termbase, shown for correction before anything is written. ### Duplicates A pair the termbase already holds is skipped – matched without regard to case, and either way round, so *method → werkwijze* is the same pair as *werkwijze → method*. The report says how many were skipped. This is the same rule Supervertaler for Trados applies to its own import, so the same file through either product leaves the same termbase, and re-importing a file is always safe. ### What Export… writes Two shapes, chosen in the save dialog: * **Supervertaler glossary (.txt)** – the `#`-header format above. Re-imports into Supervertaler for memoQ exactly. * **Tab-separated with a header row (.tsv)** – the first shape above, for a spreadsheet or for Supervertaler for Trados, whose importer expects a header row and does not skip `#` lines. Every row is exported, notes included. A term marked non-translatable in another product is exported too; re-imported, it is simply a term whose translation is itself. ### From a prompt A prompt drafted by AutoPrompt ends in a locked-terms table. **memoQ → Termbase from this prompt’s terms…** turns that table into a termbase directly, with no file in between. See [the prompt editor](/memoq/prompt-editor/#termbase-from-this-prompts-terms). # Installation ### Requirements * **memoQ 11 or 12** – translator pro or project manager edition. Earlier versions have not been tested, and the installer leaves them alone. * An API key for Anthropic, OpenAI or Google, or Claude Desktop or ChatGPT desktop if you would rather [translate through an assistant](/memoq/mcp-server/) * Administrator rights on the computer, once, while installing * *Optional:* memoQ’s free **PDF Preview tool**, which the [live document link](/memoq/mcp-server/#the-live-document-link) needs. Everything else works without it. A 14-day free trial starts by itself the first time Supervertaler runs. See [Licensing](/memoq/licensing/). ### Installing 1. **Download the installer**: [supervertaler.com/download/memoq](https://supervertaler.com/download/memoq) starts the download of the latest version. 2. **Close memoQ.** memoQ keeps its add-ins open while it runs, so they cannot be replaced underneath it. The installer checks and says so if memoQ is still open. 3. **Run the installer.** Windows asks for administrator rights, because memoQ keeps its add-ins under Program Files. The installer finds memoQ by itself; there is nothing to choose. If you have more than one version – memoQ 11 and memoQ 12, say – it installs into each of them. What it puts where: | | | | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ | | memoQ’s `Addins` folder, for example `C:\Program Files\memoQ\memoQ-12\Addins\` | the translation engine, the terminology provider, the [Supervertaler editor](/memoq/prompt-editor/) and the Claude Desktop extension | | `C:\Program Files\Supervertaler for memoQ\` | the [live document link](/memoq/mcp-server/#the-live-document-link) | | The Start menu | **Supervertaler for memoQ**, which opens the editor | ### Switching it on in memoQ memoQ does not use a new add-in until you tell it to. The installer’s last page lists the same two steps; after that, restart memoQ once. 1. **Terminology.** **Options → Terminology plugins**: tick **Perform terminology plugin lookups while working in the translation grid**, find **Supervertaler terms** in the list and tick **Enable plugin**. 2. **Translation.** **Options → Default resources → MT settings**: tick **Supervertaler** and answer **Yes** to all languages. Every new project then uses it. For a project you already have, choose it in **Project home → Settings → MT settings** instead. Then [Getting started](/memoq/getting-started/) takes you through choosing a provider and a first translation. ### The unsigned plugin warning memoQ may say, the first time it starts, that it has found one or more unsigned plugins, and ask whether to load them. **Answer Yes.** The default button is *No*, so a stray Enter keypress declines it. Supervertaler is not yet signed by memoQ. Signing is a process memoQ runs with a plugin’s author, and until it is complete this prompt can appear after an install or an update. ### Updating From version 0.1.2, Supervertaler tells you when a new version is out. Once a day it asks GitHub for the latest version, and when there is a newer one: * **the Supervertaler editor** offers it as it opens: **What’s new** opens the release notes, **Download and install** does the rest, **Skip this version** stops it being offered until the next one, and **Later** offers it again the next time the editor opens. **Help → Check for updates** asks at any time, and offers a skipped version too; * **in memoQ**, the line under Supervertaler’s hits in Translation results says that a new version is available, for anyone who never opens the editor. **Download and install** downloads the installer, checks that it is exactly the file GitHub published – its size and its checksum – and runs it, then closes the editor so its own file can be replaced. Close memoQ first; the editor says so if it is still open. The version you have is in the editor’s title bar – “Supervertaler for memoQ – v0.1.5” – from version 0.1.5 on. Versions 0.1.0 and 0.1.1 have no update check, so they are never told. If **Help** in your editor has no **Check for updates**, download the latest installer once as below; from then on you will be told. To update by hand, close memoQ and run the new installer from [supervertaler.com/download/memoq](https://supervertaler.com/download/memoq). Either way it replaces the files in place; your settings, prompts, termbases, memory banks and licence are kept, because none of them live in the program folders. ### After a memoQ upgrade memoQ’s program folder carries its version number (`memoQ-12`, `memoQ-13`, …), and a major upgrade installs into a **new** folder, without the add-ins. If Supervertaler disappears after a memoQ upgrade, this is almost always why: run the Supervertaler installer again. It installs into every memoQ it finds, from memoQ 11 up. ### Installing by hand For an IT department that deploys centrally, or if the installer cannot run: the download is also available as a zip that holds the installer and the loose files. Copy `Supervertaler.MemoQ.dll`, `Supervertaler.MemoQ.Terms.dll` and `Supervertaler.PromptEditor.exe` into memoQ’s `Addins` folder, then switch it on as above. For **memoQ 11**, also copy the contents of the zip’s `for-memoQ-11` folder into the same `Addins` folder, keeping its `runtimes` subfolder as it is. memoQ 11 does not include the database library Supervertaler’s termbases use, and these are the official builds of it; memoQ 12 has its own and needs none of them. The one in `runtimes\win-x64\native` must stay there: memoQ tries to load every `.dll` directly in `Addins` as an add-in, and that one is not. Installed this way there is no Start menu entry and no Claude Desktop extension beside the editor; [AI assistants](/memoq/mcp-server/#setting-it-up) explains the alternative. ### Uninstalling Close memoQ, then remove **Supervertaler for memoQ** in Windows **Settings → Apps → Installed apps**. Your own files stay where they are: prompts, termbases and memory banks in `C:\Users\\Supervertaler\`, which Supervertaler for Trados shares. To remove what the plugin has learned from your documents as well, use **Forget stored context** in memoQ’s Supervertaler options before uninstalling – see [Self-learning translation](/memoq/self-learning/#what-is-stored-and-where). # Licensing **One Supervertaler licence covers Supervertaler for Trados and Supervertaler for memoQ.** Use either, or both; there is no second subscription for working in a second tool. ## Free trial A **14-day free trial** starts by itself the first time Supervertaler runs. Everything works during the trial, and there is nothing to sign up for and no card to enter. The trial belongs to the computer rather than to the plugin, so if you have already tried Supervertaler for Trados on this computer, the memoQ plugin shares the same trial. To see how many days are left, open **Supervertaler for memoQ** from the Start menu and choose **Help → Licence**. ## Pricing | | Monthly | Annual | | ---------------------------------------- | --------- | --------------------------- | | **Supervertaler** – for Trados and memoQ | €20/month | €200/year (two months free) | See [supervertaler.com/pricing](https://supervertaler.com/pricing/). Teams, invoicing and reduced rates are there too. ## Buying and activating 1. Subscribe at [supervertaler.com/buy](https://supervertaler.com/buy). Your licence key arrives by email. 2. Open **Supervertaler for memoQ** from the Start menu and choose **Help → Licence**. 3. Paste the key and click **Activate**. The licence window then reads **Licensed**, with the key shown masked and the date it was last confirmed online. ### Already subscribed for Trados? Then you already have Supervertaler for memoQ. On a computer where the Trados plugin is activated with a current version, the memoQ plugin picks up the licence by itself: open **Help → Licence** and it already reads *Licensed*. On any other computer, enter the same key. ## Computers A licence can be active on **two computers** – a desktop and a laptop, say. Both plugins on one computer count as **one** of the two, whichever of them the key was entered in. To move the licence to another computer, open **Help → Licence** on the old one and click **Deactivate this computer**. That frees it for Supervertaler for Trados on that computer as well, since it is the same licence. From v0.1.9, **a licence counts only for the computer and Windows account that activated it**. If you rename your computer or reinstall Windows, Supervertaler sees a new computer: the editor tells you so when it opens, everything stays available that day, and entering your licence key again in **Help → Licence** activates it here. The same goes for a colleague using the same data folder – each person activates their own copy of the licence. ## When a licence lapses Only **AI translation** pauses. Terminology, termbases, prompts, memory banks and the editor all keep working, and nothing you have made is lost. There are two ways to get there, and they need opposite fixes: * **The free trial has ended.** Enter a licence key under **Help → Licence**. * **A licensed computer has been offline for 30 days.** Nothing needs buying: connect to the internet, open **Help → Licence** and click **Check now**. While AI translation is paused, memoQ shows why under the grid for each segment it asks Supervertaler about, so a Pre-translate run tells you rather than failing silently. If Supervertaler cannot read its licence at all, it keeps working and tries again the next time it starts. It never pauses your work because of a missing answer. ## Managing your subscription Payment details and cancellation are handled by Lemon Squeezy, through the link in your receipt email. Supervertaler for Trados also has a **Manage subscription** link in its Licence tab. ## Privacy The licence check sends your licence key and an anonymous machine identifier to Lemon Squeezy, the payment provider, and nothing else – no translation content, file names or project details. During the free trial, memoQ also registers the trial with Supervertaler’s licence server each time it starts (from version 0.1.1): the same anonymous machine identifier, the plugin and memoQ versions, your system language and the trial’s start date and status. It gives the trial one reliable start date, as Supervertaler for Trados does, and it never slows memoQ down; without a connection the trial works exactly the same. See the [privacy policy](https://supervertaler.com/privacy/#memoq). # AI Assistants (Claude Desktop, ChatGPT) Supervertaler for memoQ can connect **Claude Desktop** or **ChatGPT desktop** – or any AI app that runs a local MCP server – to your live memoQ project. You chat in the assistant’s window; it reads the document you are translating, your confirmed segments and your termbases, and translates for you. The tokens are billed to your Claude or ChatGPT subscription, not to an API key. Setting either one up is a button in the editor: see [Setting it up](#setting-it-up). It is the same [Supervertaler MCP Server](/trados/mcp-server/) the Trados plugin uses. What differs is what memoQ lets a plugin do – which is a good deal less than Trados – so read [What it can and cannot do](#what-it-can-and-cannot-do) before you expect Trados behaviour. > **Which AI apps work?** The same answer as for Trados: any app that runs a **local (STDIO) MCP server on your own machine** – Claude Desktop, ChatGPT’s desktop app, Claude Code. Cloud-hosted clients (the claude.ai and chatgpt.com websites) have no route to a bridge that lives on your PC. ## The one thing to understand first **memoQ never lets a plugin write into the grid.** A plugin cannot move your cursor, edit a segment or confirm anything. It can only *answer when memoQ asks it for a translation*. So Claude does not write translations into memoQ. It **stages** them. They wait inside the plugin until you run **Pre-translate** (or land on the segment), at which point memoQ asks Supervertaler for a translation and receives Claude’s. Every write into your document goes through your own hands – which is not a limitation so much as a built-in review step. The other half: a plugin only *sees* what memoQ sends it. Claude cannot read your document until Supervertaler has been shown it. One Pre-translate pass does that. ## The workflow With everything set up (below), a chat-driven job looks like this: 1. **Open the project** in memoQ and tick **Pre-translate via Claude Desktop (MCP)** in Supervertaler’s settings (see [The checkbox](#the-checkbox)). 2. **Pre-translate** with Supervertaler as the MT engine. It is instant and free: the grid stays empty, but Supervertaler now holds every source segment. 3. **In Claude Desktop or ChatGPT:** *“Read my memoQ project and translate it into Dutch.”* The assistant reads the segments, checks your termbases, and stages translations. Nothing has changed in memoQ yet. 4. **Pre-translate again.** The grid fills. Each row is marked `Claude (staged via Supervertaler MCP)` in Translation results. 5. **Confirm as you go.** If [Self-learning](/memoq/self-learning/) is on, each confirmation is visible to Claude too – *“what have I confirmed so far?”* – so a mid-job conversation about terminology is grounded in your actual choices. Rows Claude has not staged still get a live suggestion from the model as you land on them, exactly as before. The checkbox only changes what **Pre-translate** does. ## The checkbox Either in the [prompt editor](/memoq/prompt-editor/), on the **Settings** menu, which needs no project open and no memoQ running, or in memoQ under **Resource console → MT settings → Supervertaler → Configure plugin**: > ☐ **Pre-translate via Claude Desktop (MCP) instead of the API key above** *Pre-translate then only hands the segments to the chat and inserts the translations it sends back; nothing is charged to the API key. Suggestions as you move through segments still use the API key.* Both paths call an AI model. The checkbox decides **which one pays and who drives**: unticked, this plugin translates through the API key you entered; ticked, Pre-translate leaves the translating to the chat app, billed to that subscription. | | Pre-translate | Landing on a segment | | ---------------------- | --------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | | **Unticked** (default) | This plugin translates every segment through your API key. Staged translations are used first where they exist. | Live suggestion from the model; staged first if present. | | **Ticked** | Hands the segments to the chat and inserts what it sends back. Nothing charged to the API key. | Unchanged – live suggestion from the model. | Two consequences worth knowing: * **You never have to toggle it mid-job.** Ticked is right for the whole of a chat-driven job: the capture pass is free, the delivery pass is free, and walking the document afterwards still gives you live suggestions for anything Claude did not cover. * **It is one switch for the whole installation, not a project setting.** It says how you are working at this moment, so the editor and memoQ show the same state and either can change it. * **Staged translations come through in either state.** Ticking the box is never a way to lose Claude’s work; unticking it is never a way to block it. It only decides whether *Pre-translate* spends API money on rows nothing was staged for. Leave it unticked if you use Supervertaler as an ordinary MT engine with no chat involved. That is the default, and it is what most memoQ users will want. ## Setting it up Open **Supervertaler for memoQ** from the Start menu and choose **Settings → Connect AI assistant…**. Set up either assistant, or both. ### ChatGPT desktop Press **Set up ChatGPT desktop**. Supervertaler fetches the server ChatGPT needs, keeps it in your Supervertaler folder, and adds one entry to ChatGPT’s own settings file – leaving everything else in that file alone, and keeping a dated copy of it first. Restart ChatGPT desktop afterwards. The same entry is read by Codex CLI and the Codex extension for VS Code, since they share ChatGPT’s settings file. If you also use Supervertaler for Trados, the two register side by side and each reaches its own CAT tool. ### Claude Desktop Claude Desktop installs extensions from inside its own settings, so this is two steps rather than one: 1. Press **Show me the extension**. It opens the folder with `Supervertaler-for-memoQ-MCP-Server.mcpb` selected and puts the file’s location on the clipboard. Nothing is downloaded: the installer put it there. 2. In Claude Desktop, open **Settings → Extensions → Advanced settings → Install extension…** and paste the location when it asks for a file. Double-clicking the `.mcpb` file works on some computers and not on others, for reasons inside Windows rather than Supervertaler; the route above works everywhere. Dragging the file onto Claude does not work. If you also use the Trados plugin, both extensions coexist – Claude shows them as two servers – and they are in fact the same server: the memoQ one carries a single setting, `SUPERVERTALER_HOST=memoq`, which tells it to look for memoQ’s connection instead of Trados’s. ### Checking it works In memoQ, open a project and click into any segment with Supervertaler selected as the MT engine – that is what starts the plugin’s side of the connection. Then ask the assistant: *“What’s in my memoQ project?”* If it answers with your language pair and segment count, you are connected. ### Other MCP clients Claude Code, or anything else that runs a local STDIO server: set up ChatGPT desktop once as above, which puts the server at `C:\Users\\Supervertaler\memoq\mcp\SupervertalerMcpServer.exe`, and register that with the one environment variable set: ```json "supervertaler-memoq": { "command": "C:\\Users\\\\Supervertaler\\memoq\\mcp\\SupervertalerMcpServer.exe", "args": [], "env": { "SUPERVERTALER_HOST": "memoq" } } ``` The server finds memoQ’s connection file in your Supervertaler data folder (`C:\Users\\Supervertaler\memoq\runtime\bridge.json`, or wherever you moved that folder). If you ever need to point it somewhere else, `SUPERVERTALER_BRIDGE_FILE` with a full path overrides it. ## The live document link memoQ’s MT plugin interface never shows a plugin the target text, the row you are on, or even the document’s name. memoQ’s **Preview SDK** – the interface its own PDF and video preview tools use – shows all three, live. So Supervertaler ships a small preview tool, `Supervertaler.MemoQ.Preview.exe`, which registers with memoQ exactly as the PDF preview does and forwards what memoQ sends it to the plugin. It needs memoQ’s own **PDF Preview tool** installed – a free download from memoQ – because that is where the interface it talks to lives, and Supervertaler ships none of memoQ’s code. The installer tells you at the end if it is missing. Nothing else in Supervertaler needs it. With it running, Claude sees your document as it actually is: every row’s current target, memoQ’s own row order, the document’s real name, and the row your cursor is on – and it can ask memoQ to **jump to a segment**. **Setting it up (once):** there is nothing to start by hand. The first time memoQ loads Supervertaler after installing, Supervertaler starts the link itself, as long as memoQ’s PDF Preview tool is installed. A tray icon appears, and: 1. memoQ asks, once, whether to accept the **Preview tool connection request** for *Supervertaler*. Accept it, leaving *Auto-start with memoQ* ticked. From then on memoQ starts the tool itself. 2. The tray icon reads *memoQ: connected · plugin: connected* once you click into a segment (that is what starts the plugin’s bridge). Supervertaler starts it only that once, so if you decline the request you are not asked again at every start. To set it up later – or if you installed the PDF Preview tool afterwards and the link has not appeared – start `C:\Program Files\Supervertaler for memoQ\Supervertaler.MemoQ.Preview.exe` once yourself with memoQ running. It appears under **Options → External preview tools** alongside any other preview tools; it can be disabled there like any of them. It draws nothing on screen – it is a link, not a preview. One thing to know: memoQ’s Preview SDK works in **paragraphs**, not segments. A paragraph that memoQ splits into three grid rows arrives as one unit with the whole paragraph’s source and target. The active-segment tool still reports the exact sentence your cursor is on, and jumps can target a sentence within a paragraph. Without the tool running, the tools below fall back to what the plugin captured from translation requests, and the two cursor tools say so rather than guessing. ## What it can and cannot do Everything the Trados server can do that memoQ *cannot* comes down to one fact: memoQ has no project API and no editor API for plugins. The live document link recovers the reading half of that; writing into the document still goes through you. The table is the honest map. | Tool | memoQ | Notes | | ---------------------------------------------------------------- | :---: | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `help` | ✓ | A menu of what you can ask, memoQ edition | | `get_project` | ✓ | Language pair, client/domain/subject, captured and live documents, what is staged | | `get_segments` | ✓ | With the live link: rows in memoQ’s order with source, **target**, and the active row marked – plus, for rows memoQ has already asked about, the source with its inline tags, so Claude can put bold, italics and other tags in the right places. Without: the source segments captured from translation requests | | `get_active_segment` | ✓ | The row your cursor is on, with what is selected – needs the live link | | `go_to_segment` | ✓ | Asks memoQ to select a row – needs the live link | | `get_confirmed_pairs` | ✓ | Segments you have confirmed, via [Self-learning](/memoq/self-learning/) | | `lookup_term` / `add_term` | ✓ | Your Supervertaler [termbases](/memoq/terminology/), not memoQ’s term bases. `add_term` writes to the project termbase | | `stage_translations` | ✓ | **The write channel.** Translations wait until you Pre-translate | | `get_staged` / `clear_staged` | ✓ | Inspect and reset the staging area | | `list_prompts` / `get_prompt` / `save_prompt` | ✓ | The shared [prompt library](/memoq/prompt-editor/). A prompt Claude saves is recorded as drafted by the chat and marked for memoQ, so it does not appear in Trados’s list and the runtime treats its terminology the way it treats [AutoPrompt’s](/memoq/prompt-editor/#a-drafted-prompt-is-the-only-source-of-terminology) | | `list_supermemory_banks` | ✓ | Your [memory banks](#memory-banks), and how many articles each holds | | `get_supermemory_context` | ✓ | One bank’s brief, terminology and style, formatted for the model | | `search_supermemory` | ✓ | Full-text search inside a bank | | `update_segments`, `insert_into_active_segment` | ✗ | No write access to the editor – use `stage_translations` + Pre-translate | | `search_tm`, `search_studio_tm`, `compare_document_to_tm` | ✗ | memoQ’s TMs are not readable by plugins; confirmed pairs are the substitute | | `check_numbers`, `check_tags`, `check_nbsp`, `check_terminology` | ✓ | QA over the live document, paragraph by paragraph – needs the live link. `check_terminology` runs against the termbases ticked Read, so give it a project one: [Termbase from this prompt’s terms](/memoq/prompt-editor/#termbase-from-this-prompts-terms) from an AutoPrompt draft | | `find_inconsistencies` | ✓ | Repeated source paragraphs translated differently – needs the live link | | `run_verification` | ✗ | memoQ’s own QA cannot be run by a plugin; use memoQ’s Run QA | | `get_files`, `get_project_statistics`, `export_target` | ✗ | No project or file API | | `pretranslate` | ✗ | You press Pre-translate; that is the design | **Reading is complete with the live link; writing goes through you.** What you give up compared with Trados is Claude editing rows in place – and in memoQ the alternative, staging plus one Pre-translate, is a review step rather than a loss. ## Two channels for seeing the document Supervertaler captures segments in two ways, and it helps to know which is which when Claude reports what it can see: * **Translation requests** – every segment memoQ sends to Supervertaler as the MT engine. One Pre-translate captures the whole document, with its identity and metadata. This is the normal route. * **Terminology lookups** – every row your cursor lands on, through the [terminology plugin](/memoq/terminology/), *regardless of which MT engine is selected*. So a document you pre-translated with Google or from TM alone still becomes visible to Claude one visited row at a time. memoQ does not tell the terminology plugin which document a row belongs to, so these land in a per-language-pair bucket rather than under the document. `get_project` labels each captured document with its origin. ## Memory banks If you keep [SuperMemory](/trados/ai-assistant/super-memory/) banks – a folder per client, holding the brief, the terminology and the style rules you have settled on with them – Claude can read them here too. They live in one place for every Supervertaler product: ```plaintext C:\Users\\Supervertaler\memory-banks\ ``` Ask for what you want and Claude picks the tool: *“list my memory banks”*, *“read the Acme bank before you translate this”*, *“search the Acme bank for how we render ‘Vorrichtung’”*. Four things behave differently from the Trados plugin, and they are worth knowing before you rely on this: * **Claude is not told which bank is active.** You choose one in the [editor’s context bar](/memoq/prompt-editor/#what-memoq-is-using), and it is remembered per project – but that is what the plugin sends with its own translation requests. Over MCP the bank is named in the request instead, so say which one you mean. Claude will ask, or list them and let you choose. * **A name that does not exist is an error**, not a fall back to something else. Falling back would look exactly like success while feeding the model another client’s terminology, and nothing in the answer would say so. * **`_shared` is always underneath, and travels alone.** It is not a bank you select: whatever you do select is layered over it and wins wherever the two disagree – and when you select no client bank, `_shared` still goes on its own. Choosing “no client bank” is not the same as sending nothing. * **The answer is trimmed to about 6,000 tokens**, and whatever did not fit is listed under `trimmed` in the reply rather than dropped in silence. A tool result stays in the conversation and is re-sent on every following turn, so it is kept deliberately small – ask for a larger budget, or for one article by name, when you need the rest. Reading is all this does. Nothing writes into a bank from memoQ; you edit the files yourself, in Obsidian or any text editor. ## Troubleshooting **“Handshake file not found.”** memoQ has not created a Supervertaler engine yet in this session. Open a project and click into a segment with Supervertaler selected as the MT engine. **Claude says the project is empty.** Nothing has been captured yet. Run Pre-translate once, or visit some segments. **Staged translations do not appear after Pre-translate.** They are matched by source text, with inline tags and spacing set aside. If you edited a source segment after Claude read it, the match fails – ask Claude to re-read and re-stage that segment. Also check that Supervertaler is the selected MT engine for the Pre-translate run. **A staged row says “inline tags not placed”.** Claude’s translation reached the row, but without the tags the source has, so memoQ’s tag check will flag it. Ask Claude to read the segments again – it can see each row’s tags once memoQ has asked about it – and re-stage those rows with the tags in place, then Pre-translate again. **`get_confirmed_pairs` is always empty.** Self-learning is not on. See [Self-learning translation](/memoq/self-learning/). # The Supervertaler Editor memoQ gives an add-in no window of its own, so everything Supervertaler needs a window for lives in one that runs alongside memoQ: the **Supervertaler editor**. Open it from the Start menu – it is called **Supervertaler for memoQ** there – or with **Edit…** in memoQ’s own Supervertaler options dialog. It is where you choose what memoQ uses for each job (model, prompt, memory bank, termbases), edit the **shared Supervertaler prompt library** – the same folder of prompts the Trados plugin uses, so a prompt tuned in one tool is available in the other – draft prompts with [AutoPrompt](#autoprompt-drafting-a-prompt-for-the-open-project), describe a document’s figures with [FigureLens](#figurelens), watch what the plugin is doing in the [Activity window](#the-activity-window), connect [AI assistants](/memoq/mcp-server/#setting-it-up) and manage your [licence](/memoq/licensing/). Instructions can also be typed straight into memoQ’s settings dialog instead of coming from the library. ## Choosing a prompt In **Resource console → MT settings → Supervertaler → Configure plugin**, the **Prompt** dropdown lists every translation prompt in the library, grouped by folder. Pick one and its text appears (read-only) in the **Instructions** box below. Choose **(instructions below)** instead to type your own; the box becomes editable. The dropdown stores *which* prompt you chose, not its text. Edit the prompt anywhere – in the editor, in the Trados plugin, in a text editor – and memoQ uses the new version on the next segment. Only prompts in the library’s **Translate** folder are offered. Proofreading and QuickLauncher prompts exist for other tasks and would produce commentary where a translation belongs. ## The editor Open **Supervertaler for memoQ** from the Start menu, or press **Edit…** beside the Prompt dropdown in memoQ’s options dialog. * **Left:** the library as a tree, folders and prompts. Select one to open it. * **Right:** name, description, which product it is for, sort order, and the prompt text with Markdown headings and `{{PLACEHOLDERS}}` highlighted. * **Toolbar, left:** New, Save, Placeholder, AutoPrompt. * **Toolbar, right:** whether Pre-translate goes to Claude Desktop, and the [Activity window](#the-activity-window). Everything else is on the menus: **File** for the library, **memoQ** for the open job, **Settings** for [Translation settings](#settings) and [Connect AI assistant](/memoq/mcp-server/#setting-it-up), and **Help** for this documentation and your [licence](/memoq/licensing/). The **Claude Desktop** button on the right is a switch, not a command, and its caption says which mode is *on* rather than what pressing it would do. It decides whether Pre-translate spends your API key or hands the segments to the chat, so it is worth a glance before a long run. It is the same setting as **Settings → Pre-translate via Claude Desktop**, and as the checkbox in memoQ’s own dialog – change it anywhere and all three follow. Save with **Ctrl+S**. A built-in prompt – the Default Translation Prompt, say – is never saved over: your changes are saved as a prompt of your own, named ”… (my version)” unless you gave it a new name, and it becomes the active prompt if the original was. The built-in one stays as it shipped, so an update to it can never overwrite your work. Any settings the file carries that the editor does not have a field for – tags, favourites, QuickLauncher flags set by the Trados plugin – are preserved untouched on save. The status line under the description says which ones the file has. ### What memoQ is using The bar under the toolbar opens with the **memoQ project** these apply to, because everything on it is recorded against a project. When it reads **no project yet**, in red, memoQ has not sent a translation request and the plugin does not know where it is – usually because Supervertaler is not selected as the MT engine in a newly created project. A memory bank chosen at that moment is filed against whichever project came before, silently, so it is worth a glance before changing anything. Then four things memoQ will apply to every translation: **Model**, **Prompt** and **Bank**. Click any of them to change it. Each opens a list with a filter box rather than a dropdown menu, because they grow with the work – a prompt library reaches forty entries quickly, and a bank per client does the same. The bank can also be set to nothing. **Termbases** is the fourth row, and it is a summary rather than a picker: *BRANTS (project) + BEIJER · 1 of 2 to the model* – which termbases are ticked for this project, which of them is the project’s, and how many reach the model. A termbase selection is a set, and a dropdown cannot hold one; clicking the row opens the [Termbases window](/memoq/terminology/#the-termbases-window), which can. It reads *none* in grey when terminology is off. These are the choices that change between jobs, which is why they are here rather than in Translation settings: they are what the model knows before it is shown a segment. Each is also the same setting memoQ’s own dialog shows, so either place can change it. The memory bank is remembered **per project**. Choose one while working on a job and it comes back when you return to that job – and a project you have never chosen one for does *not* inherit the last one, because a bank carries one client’s terminology and the wrong one is worse than none. What such a project gets instead is the row called **(no client bank – shared defaults only)**. Your `_shared` bank still travels: it is where the material that applies to every job regardless of client lives, so it is never switched off by not choosing a client. See [Memory banks](/memoq/mcp-server/#memory-banks) for where they live. A bank is sent whole with **every** translation request, up to about 32,000 tokens, and to AutoPrompt up to 40,000. Anything that does not fit is dropped by priority and named in the [Activity window](#the-activity-window) rather than lost quietly – if you see a file listed there, that is the budget, not a fault. The cost of carrying it is small because the same text is sent every time and providers cache it: on one 370-segment run the bank and prompt together came to 45,870 tokens, and caching turned roughly $10 into roughly $4 – for Pre-translate and, since September 2026, for the single rows memoQ asks about as you move through the grid. **A large bank sends only what the job needs.** Once your banks together pass about 8,000 tokens, each job gets a selection instead of everything: only the terminology rows whose term occurs in the document (in either column, whichever way the table was written), and the notes the model judges relevant after reading the document, asked once per job. The client bank’s brief, style guide and domain notes always go. The house rules in `_shared` are judged one by one in the same question: a rule whose **Scope:** line clearly does not fit the job’s language pair or kind of document is left out, so a rule written for Dutch-to-English work stays out of an English-to-Dutch job. When the model is unsure, the rule goes; if the question cannot be asked – memoQ has not yet shown enough of the document, or the request fails – everything goes, as before. It happens by itself; there is nothing to set. The **Bank** row’s tooltip says when it is happening and names a file under `C:\Users\\Supervertaler\memoq\bank-extracts\` listing what was sent and what was left out, which is the place to look if a translation seems to have missed something you wrote down. **Notes for the assistants only.** Some notes are about how to work a job – what to check before delivery, how to verify a termbase – and help an AI assistant rather than a sentence being translated. Put this at the very top of such a note: ```plaintext --- audience: assistant --- ``` It is then left out of every translation request (the translation engine and AutoPrompt), while Claude Desktop and ChatGPT still read it through the Supervertaler tools. A note without it is sent as always, and the job’s selection file lists anything left out this way. You can switch the bank off altogether: **Settings → Translation settings → Send the memory bank to the model**. Off, nothing from any bank – the client’s or `_shared` – goes to the model, for translation or AutoPrompt, and the **Bank** row reads *not sent*. The bank chosen for each project is kept for when you switch it back on. ### Placeholders Prompts use `{{SOURCE_LANGUAGE}}` and `{{TARGET_LANGUAGE}}` rather than naming languages, so one prompt serves every language pair. memoQ fills them in per project. **Insert placeholder** lists the ones memoQ can fill. A placeholder memoQ cannot fill – `{{SOURCE_SEGMENT}}`, say, which only the Trados plugin provides – is shown in red, and the editor warns that it will reach the model as empty text. Do not use those in a prompt meant for memoQ. ### Which product a prompt is for **Available in** can be *both*, *trados* or *memoq*. memoQ’s dropdown hides prompts marked for Trados only. Leave it on *both* unless a prompt genuinely depends on something one product cannot supply. A prompt tied to one product says so in its **filename**: `Patent claims EN-NL [memoQ].md`, `Define [Trados].md`. Prompts available to both carry no marker, so the absence of one is itself readable – which is the point, because in Explorer the metadata header is not visible and every prompt otherwise looks alike. The marker is written from the **Available in** field on every save and stripped again on every read, so it is a label rather than a setting. Renaming the file in Explorer does not change which product a prompt is for, and the next save puts the old marker back: change the field, not the filename. The editor’s tree and the Prompt dropdown show the same thing in words. ## Where the library lives `C:\Users\\Supervertaler\prompt_library\` – one Markdown file per prompt, with a small metadata header. **Open folder** in the editor takes you there. The files are plain text; nothing stops you editing them directly, and a folder synced between machines carries the whole library with it. ## AutoPrompt: drafting a prompt for the open project Press **AutoPrompt…** in the editor’s toolbar, or choose it from the **memoQ** menu. Supervertaler reads the document you are translating, the termbase hits in it (from termbases ticked AI) and anything you have already confirmed, and has the AI write a prompt tailored to that job – domain, register, a locked glossary, the lot. The result is saved under **Translate** and opened for you to review; then pick it from memoQ’s **Prompt** dropdown. Before it runs you choose the document (if several are captured), and can add a briefing – client, audience, style, what to avoid – which the AI treats as authoritative. The briefing is the one input nothing else supplies: the filing route, a discrepancy you already know about, anything true of this job that is not in the document or the memory bank. The two checkboxes grey out when they have nothing to offer – no termbase is ticked AI for this project, or nothing has been confirmed in this document yet – and say which it is, rather than sitting there ticked and doing nothing. **Preview context…** shows you exactly what will be sent, before anything is sent: the extract from your document, the termbase hits, the segments you have confirmed, the briefing you typed, and the instructions the AI is given about writing a prompt for memoQ. It makes no API call and costs nothing, and the briefing box stays open behind it – so the loop is look, add what is missing, look again, then generate. Three things to know: * **memoQ must be running with a Supervertaler engine active**, and the document must have been captured – one Pre-translate does it (free, with the [Claude Desktop box](/memoq/mcp-server/#the-checkbox) ticked). The plugin only sees what memoQ has sent it. * **It uses the provider, model and API key from your Supervertaler settings.** Two calls: a short one to classify the document, then a long one to write the prompt. Expect a minute or two. * **The prompt is written for memoQ, not copied from the Trados recipe.** Single-segment lookups are handled as well as batches; tag markers must be reproduced exactly; translations you have confirmed outrank the prompt’s own glossary; and it is kept to 1,500–3,000 words because memoQ re-sends the whole prompt with every ten-segment request. Draft it again later in the job and it gets better: by then it can see what you have confirmed, which is stronger evidence of how you want *this* document translated than the source text alone. ### A drafted prompt is the only source of terminology A prompt AutoPrompt wrote ends in a locked-terms table chosen for this document. So while one is selected, **the termbases’ preferred renderings are not sent to the model as well** – two lists of terminology that were never written to agree, with nothing saying which wins, is a worse position than one list. **Forbidden terms still go.** A preferred rendering is advice, and two sources of advice can contradict each other confusingly; “never use this word” is a constraint, and there are few of them. So they travel whatever prompt is selected. Nothing else about the termbases changes: they still drive the terminology pane, the QA check and AutoPrompt’s own reading of the document. Only the per-request injection stops, and the [Activity window](#the-activity-window) says so once per prompt. The consequence worth remembering: a term you forbid **after** a prompt was drafted is enforced immediately, but a preferred rendering you add afterwards is not – draft the prompt again to take it in. **Termbase from this prompt’s terms** is the other half of that loop: derive the project termbase *from* the prompt and the two cannot contradict each other in the first place. Prompts saved from the chat over [MCP](/memoq/mcp-server/) count as drafted too, and are marked for the product you were connected to. ### List numbering reaches the model as structure The letters on the steps of a claim – a), b), c) – are not text. Word generates them from the paragraph’s list settings, so memoQ’s grid does not contain them and neither does anything the plugin is sent. Shown six unlabelled sentences followed by *steps a. to f.*, a model will flag the reference as a possible source defect, and it will do so on every lettered list in every document. With the [live document link](/memoq/mcp-server/#the-live-document-link) connected, the plugin knows which file memoQ imported, reads the numbering out of it – counted over the whole document, exactly as Word renders it, restarts and all – and sends each paragraph’s marker in front of its first segment as `[#e)]`. The prompt tells the model this is structure: use it to resolve cross-references and keep list items parallel, never translate it, never reproduce it. Every reply is checked before it reaches the document, and an echoed marker is removed, with a line in the [Activity window](#the-activity-window) saying so – that line is your evidence, per model, that the rule is being obeyed. There is no switch for it. Without the live link, or for a document with no lists, the model is instead told that numbering is supplied by the document and not to flag its absence. The Activity window says which of the two happened, once per document. On a project checked out from a server the file memoQ names is on the project manager’s machine, not yours; locate it once in [FigureLens](#where-the-documents-come-from) and the numbering is read from your copy. ### Translator comments Where a note is genuinely necessary – an ambiguity in the source, a term that could go two ways, a probable defect in the original, an error it corrected in a 100% translation memory match, a deliberate departure from the terminology – the AI puts it inline at the end of the target as a `[[TC: …]]` marker: one per segment at most, short, and written as your comment to the client. This is built in, not something a prompt has to ask for: every request ends with a fixed **output contract** that says so, whichever prompt is selected. A prompt can add to it – its own examples of good comments, a language other than English for them – but cannot switch it off by accident. Supervertaler for Trados uses the same form, so a prompt written for one product reads correctly in the other. ### What the model may send back The same contract says the reply is the translation and nothing else, and every reply is checked before it reaches the grid. One that carries commentary anywhere but a single trailing `[[TC: …]]` – a note after the translation, the model explaining its own choices, markdown or a line break the source does not have, a second marker – is asked for once more with the contract restated. If the second reply does the same, **nothing is written**: the row is left for you, and memoQ shows under it why, together with what the model sent, so you can still use the translation part if it was sound. Each retry and refusal appears in the [Activity window](#the-activity-window). Tags that differ from the source are reported there too, but never refused: a translation that drops a formatting tag is often right, and a row left empty for it would cost more than it saves. A row whose source has nothing to translate – only a placeholder tag, spaces or punctuation – is not sent to the model at all. Its source is copied into the target, tags intact. Nothing extracts these for you, and that is deliberate. You read them in the grid as you review, decide which are worth keeping, turn those into real memoQ comments on the segment, and delete the marker from the text. Search for `[[TC:` to find them all. ## FigureLens The model sees a document’s text and not its pictures. A claim that names *part 12* is translated by a model that has never seen part 12, and a figure’s caption is often the only description of it anywhere in the text. **FigureLens…** on the toolbar (also **memoQ → FigureLens…**) is the panel that closes that gap, in two steps. It is named for what it does beside [TermLens](/memoq/terminology/): that one shows the model the terms in a segment, this one shows it the pictures. **Step 1 – Extract images** copies every image out of the documents into the active memory bank’s `figures\` folder, named after their figure numbers – `Figure 01.png`, `Figure 02.png` – so a folder of drawings reads like the document. Free, no AI. The panel says how the labels were arrived at: paired by position and checked, taken from nearby text, or withheld when it could not tell. **Step 2 – Describe images with AI** shows each image to the model, together with what the text says about it, and saves the descriptions as `figures.md` in the memory bank – one paid request per image, and the panel states the count and the provider before you click. Every prompt reads that file from then on, so read it first: a wrong caption would be invisible and everywhere. Reference signs the model reads in a drawing that appear nowhere in the text are listed at the end, because that is a defect worth raising with the client before filing. **Describe from the text only** is the free alternative – what the document itself says about each figure, without looking at the images – and either replaces the other, after asking. The images folder is not chosen: it is inside the memory bank, because that is where `figures.md` goes and the two belong together. With the shared bank or no bank active, the Result line offers to create a bank named after the memoQ project and switch to it. ### Where the documents come from memoQ never keeps the original file in its project folder – a local project stores the filename as an empty placeholder, a project checked out from a server stores only memoQ’s own data – so the panel works from the file memoQ imported, wherever that was: * On a **local project**, the [live document link](/memoq/mcp-server/#the-live-document-link) reports the path memoQ imported each document from, and the panel finds the file there without any setting. * On a **server project**, memoQ records the path the file had on the project manager’s machine, which does not exist on yours. The panel lists those documents as *not on this computer* and offers **Locate the original document…** – point it at the copy you were sent, once, and it is remembered for that document in `C:\Users\\AppData\Local\Supervertaler.memoQ\document-files.txt`. Locating a document here also switches on [list numbering](#list-numbering-reaches-the-model-as-structure) for it. * **Add a document file…** is for a Word file memoQ has said nothing about at all. Its images are read from the file directly; the file is remembered for the active memory bank. Supervertaler finds the project folder by asking memoQ where it keeps its projects – the custom folder set under **Options → Locations → Projects**, the default `C:\Users\\Documents\My memoQ projects` when you have not set one, and memoQ’s own register of every project, which names each one’s actual folder. Moving your projects folder therefore needs nothing here, and projects left behind in the old location are still found. **Document images report** at the bottom writes a Markdown listing of every image in every document – label, size, caption, the text around it – into the memory bank and opens it. No AI call. ## Termbase from this prompt’s terms An AutoPrompt draft ends with a locked-terms table – a dozen or so renderings chosen for this document. That table is exactly what the [terminology plugin](/memoq/terminology/) and the `check_terminology` QA tool should work from: a general termbase flags *application → aanvrage* in every paragraph of a software text, a project termbase knows better. Choose **memoQ → Termbase from this prompt’s terms…** with the prompt open. Supervertaler reads every table in it that names a source and a target column, turns notes of the form *never “apparatus”* into forbidden entries, and makes a termbase named after the prompt – or adds to it if one exists, skipping pairs already there – and ticks it Read and Project for the current memoQ project. A row that lists alternates, *regenereren / regeneratie | regenerate / regeneration*, becomes one pair per alternate. It works whether or not memoQ is running; memoQ picks the change up within a few seconds. Any prompt with a table laid out the same way works, not only AutoPrompt’s. Correcting the result afterwards is what the Terms window is for; rows the prompt no longer has are not removed, since they may have been corrected by hand. ### Settings **Settings → Translation settings** holds how Supervertaler translates: provider, model, endpoint, parallel requests, segments per request, and whether termbase hits, surrounding segments and the memory bank are sent to the model. These are the same settings as memoQ’s own Supervertaler dialog, reading and writing the same file, so either place can change them and both show the same values. The **Model** list is short on purpose: three to five models per provider, each with a line saying what it is for. A provider’s own catalogue runs to thirty or forty entries – image models, speech models, dated snapshots of the same model – and a list like that is one nobody in a hurry can choose from. A model that has been superseded is removed rather than annotated, so what is left is what is worth using today. **Fetch list** asks the provider for its full list, using the API key below. **Show all models** then shows everything it returned under the short list, which is where to look for a model released after your copy of Supervertaler was built. The fetched list is remembered, and so is the tick, so this is a decision you make once. The line under the button says when the list was last fetched and how much of it is beyond the short list. The box stays typeable throughout, so a gateway, a private deployment or a model that appears in neither list can be entered by hand – and a model already saved in your settings keeps working whether or not it is in the list on screen. Changing the provider changes three things together: the model list, the model itself – to that provider’s first recommendation, since a model belonging to another provider can only fail – and the API key, which is re-read for the provider you have just chosen. A key you type here is remembered per provider while the window is open. memoQ’s own **Configure plugin** dialog has the same three controls, reading and writing the same settings, so it does not matter which one you use. **Segments per request** can only lower what memoQ does, not raise it – memoQ hands a plugin about ten segments at a time during Pre-translate, however high this is set. Lowering it is still worth doing if a model keeps returning fewer translations than it was sent. **Send anonymous usage statistics when memoQ starts** (from version 0.1.1) is your answer to the question the editor asks the first time it opens. If it is ticked, memoQ sends one small message each time it starts: a random ID, the plugin version, the Windows and memoQ versions and your system language – never your documents, translations, terminology or file names. Nothing is sent unless you tick it. See the [privacy policy](https://supervertaler.com/privacy/#memoq). **Settings → Pre-translate via Claude Desktop (MCP)** is on the menu itself, and on the right of the toolbar, because it is the one that gets flipped between jobs rather than set once. See [MCP server](/memoq/mcp-server/). ### API keys live in one file Every Supervertaler product reads the same file: ```plaintext C:\Users\\Supervertaler\settings\api-keys.json ``` One key per provider, plain text, editable in Notepad. A key pasted here works in Supervertaler for Trados and Supervertaler Sidekick as well, and rotating one means changing one line in one place. Before this file existed there were three dialogs in three products each keeping their own, which is how an hour goes missing to a key for one service pasted into another’s box. Keys are stored under the provider ids `claude`, `openai` and `gemini`. Sidekick keeps its machine-translation keys in the same file under their own names – note that `google` there is Google Translate, not Gemini. Plain text is deliberate, and the same choice Supervertaler for Trados has always made: a key that can be rotated by pasting a line into a text file is a key that actually gets rotated, and anyone who can read that file can already read everything else in your profile. The **API key** box shows the key for the provider you have selected and writes back to that file. If you had a key configured before the file existed – in memoQ’s own settings, or in Trados’s – it is copied in the first time Supervertaler needs it, so there is nothing to do. If you paste a key that plainly belongs to another service, the line under the box says so as you type: *This is an OpenAI key, not an Anthropic one.* That is worth more than the provider’s own answer, which is that the key is incorrect. ## The Activity window memoQ’s Pre-translate dialog is modal and says only *Processing*, for as long as the run takes: no engine, no model, no count, and no sign when something is wrong. **memoQ → Activity…**, or **Ctrl+L**, opens a window that shows what Supervertaler is actually doing. It is a window of its own rather than a panel so that it can sit over memoQ while that dialog holds the screen. Tick **Keep on top** and you can watch a Pre-translate run from the first batch to the last. What it shows: the engine and model each project starts with, the termbases as they load and how many terms came out of them, a warning when the selected prompt faces the opposite language pair, every batch with the segments sent, the segments returned and the terms matched, AutoPrompt drafts, and anything that failed. A batch that comes back short is called out rather than logged flatly, because that is the failure that quietly shifts every translation after it. Five lines are worth knowing by sight: * **Bank** – which memory bank a project switched to, and once per job how much of it is being sent. If it ends with a file listed as *not sent*, that is the budget trimming by priority, not a fault. * **Terminology** – said once when a drafted prompt is holding the termbases’ preferred renderings back, so a quiet change to what reaches the model is never silent. * **Rows** – after each Pre-translate call, where its rows came from: how many were staged by an assistant, how many the model wrote, how many were copied because there was nothing to translate, and how many were left for you. Staged and model-written rows look the same in the grid; this is where the difference shows, and the totals line adds them up over the run. * **Reply** – a reply that broke the [output contract](#what-the-model-may-send-back): asked for again, refused, or served with tags that differ from the source. * **The token count on each batch** – `tokens: in 1,041 (cache write 45,870) out 1,233`. The prompt and the bank are identical on every request of a run, so providers cache them: the first batch writes, the rest read at a tenth of the rate. If *cached* never appears across a long run, something is re-sending the block at full price. **Show everything** un-hides the per-request diagnostics – memoQ’s capability probes, lookup sessions, single-segment translations – which are what you want when something is wrong and noise the rest of the time. The window reads the plugin’s own log, `C:\Users\\AppData\Local\Supervertaler.memoQ\plugin.log`, rather than being fed by the plugin. So it shows what happened before you opened it, it works whether or not memoQ is running, and closing it costs nothing. Its position and size are remembered. ## Drafting prompts with Claude If you use the [MCP server](/memoq/mcp-server/), Claude can write into this library: *“Draft a translation prompt for this project and save it.”* It reads the captured document, your confirmed segments and your termbases, saves the result as a new prompt, and you pick it from the dropdown. The editor is where you review and tune what it wrote. # Self-learning Translation Supervertaler remembers the segments you confirm, and shows the most relevant ones to the model when it translates later segments in the same document. This is what makes the second half of a document read like the first. Settle on a rendering once, confirm it, and everything that follows is translated with your choice in front of the model rather than against a blank slate. ### Turning it on **Resource console → MT settings → your resource → Settings tab → Self-learning MT → Supervertaler.** Then restart memoQ. Until this is set, memoQ never passes confirmed segments to the plugin, and Supervertaler translates without memory. ### What gets remembered Only segments **you confirm**. Not the AI’s raw output. That distinction is deliberate. Feeding a machine its own guesses compounds its mistakes; the value of these examples is precisely that a human approved them. For each confirmation Supervertaler stores the source text and the target text, and nothing else – no tags, no formatting, no metadata. Re-confirming a segment replaces the earlier version, so your latest decision is the one that counts. ### How much is sent to the AI Not all of it. For each new segment, Supervertaler picks the **five** stored pairs sharing the most vocabulary with it. A pair with no words in common is never sent. So a document with hundreds of confirmed segments still contributes only a few short examples per request – the ones most likely to matter. ### What is stored, and where Memory is kept per document *and* language pair, and written to: ```plaintext C:\Users\\AppData\Local\Supervertaler.memoQ\document-memory\ ``` It survives closing memoQ, so picking a job back up the next morning keeps yesterday’s decisions. Limits: 500 pairs per document, 200 documents, and anything untouched for 60 days is discarded. This is client text on your disk These files contain source and target segments from real work. They are stored under your own user profile, are not synced anywhere, and never leave your computer. The plugin’s options dialog shows how many documents and how much space are held, with a **Forget stored context** button that deletes all of it. Your translations in memoQ are not affected. ### What it is not This is not adaptive machine translation in the sense that ModernMT or Lara mean it. No model is trained or fine-tuned, and nothing is sent to Supervertaler – the examples are simply included in the request to the AI provider you chose, alongside the segment. The practical differences: it works within a document rather than across your whole history, it is lost if you clear it, and it is entirely inspectable. Nothing happens that you cannot see in the prompt. # Terminology Supervertaler keeps your terminology in **termbases** – the same termbases Supervertaler for Trados and Supervertaler Workbench use, in one shared database – and uses them in two places at once: memoQ’s terminology pane, and the AI’s prompt. ### Why termbases, and not memoQ’s own term bases memoQ does not let a plugin read its own term bases. A term base attached to your project is visible to you and to memoQ’s QA, but not to a machine-translation plugin – so a term marked forbidden in memoQ will not, on its own, stop the AI using it. memoQ confirmed this in September 2026: today the only route is their server API, and a new integration endpoint that will pass terminology to MT plugins is planned for around the start of 2027. Supervertaler works around it by being a terminology source in its own right. Terms in its termbases reach the model because Supervertaler puts them there, and reach memoQ’s grid and pane because Supervertaler is also a terminology provider memoQ consults. ### Where termbases live One database, `C:\Users\\Supervertaler\resources\supervertaler.db`, shared by all three Supervertaler products. A termbase you create in memoQ is there for Supervertaler for Trados the moment you press OK, and the other way round. If you own only Supervertaler for memoQ, the database is created the first time you make or import a termbase – you need nothing else. What is *not* shared is which termbases a given product uses. Those choices are memoQ’s own, kept in `C:\Users\\Supervertaler\memoq\termbases.txt`, so ticking a termbase for a memoQ project changes nothing in Trados. ### The Termbases window **memoQ → Termbases…** in the [prompt editor](/memoq/prompt-editor/), or click the **Termbases** row in its context bar. One row per termbase in the database, with four ticks: | Tick | Scope | Meaning | | ----------- | ------------------ | -------------------------------------------------------------------------------------------------------------------------------- | | **Read** | this memoQ project | Consult it: its terms highlight in the grid and appear in the pane. | | **Project** | the termbase | This job’s own termbase – at most one. Its hits are shaded darker, and it is where a term added from the grid or by Claude goes. | | **CS** | the termbase | Match its terms case-sensitively. Useful for abbreviations. | | **AI** | the termbase | Send its matched terms to the model. Without it a termbase is for your eyes only. | Read is per project, which is why the project is named at the top of the window; the other three belong to the termbase and apply wherever it is used. The line under the table tallies what you have ticked – how many termbases, how many terms, whether one is the project’s, how many reach the model. The window opens on the project memoQ last sent a segment from. In a new project, translate one segment first, or the ticks would be filed against the previous job. If you also use Supervertaler for Trados, the termbase it treats as the project termbase starts out ticked Project here, so you do not nominate it twice. It is a starting answer, not a link: change it here and memoQ keeps its own from then on. **Read and AI are separate decisions on purpose.** A large general termbase is often worth *seeing* – every hit in the grid, every entry in the pane – without being worth *sending*: ten thousand generic renderings in a prompt crowd out the dozen that matter for this document. Tick Read on the big one and AI only on the project’s. ### Making, filling and managing termbases The buttons along the bottom of the Termbases window: * **Terms…** – or double-click a termbase – opens its terms in a grid: source, target, a Forbidden tick and a note, with a filter box for the large ones. Type in the empty last row to add a term, edit a cell to correct one, select and remove one. OK writes everything, Cancel discards it. A pair the termbase already holds, either way round, is refused by name and the rest of your edits still go through. * **New…** makes an empty termbase. You type the name and the two languages as codes – `nl`, `dut-NL`, `Dutch` all work – and the form says back what it understood. * **Import…** makes a termbase from a file: a memoQ or Excel export, a Trados export, or one of the glossary files older versions of Supervertaler used. The file’s own header supplies the name and languages where it has one, shown for correction before anything is written. See [Importing and exporting](/memoq/glossary-format/). * **Add to…** pours a file into an existing termbase. If the file runs the other way round from the termbase it is turned; pairs already present, either way round, are skipped – the same rule Supervertaler for Trados applies, so the same file through either product leaves the same termbase. * **Export…** writes a termbase out, as a Supervertaler glossary file or as a tab-separated file with a header row for a spreadsheet or for Trados. * **Delete** removes the termbase, its terms and its synonyms – for Supervertaler for Trados and Workbench as well, since they share the database. It says so before it does it. A termbase you make here is ticked Read for the current project as it is made. ### Setting it up in memoQ **Options → Terminology plugins.** 1. Tick **Perform terminology plugin lookups while working in the translation grid**. Nothing happens until this is on. 2. Find **Supervertaler terms** in the list and tick **Enable plugin**. Its **Options** button opens the prompt editor, which is where terminology is managed. That is all: a terminology plugin applies to every project, and does not appear in **Project home → Term bases**, which lists memoQ’s own term bases only. Restart memoQ after enabling the plugin for the first time. After that, a termbase you tick Read in the [Termbases window](#the-termbases-window) shows its terms on the next segment you land on, with memoQ left open. Up to v0.1.10 it did not: *Supervertaler terms* read *Not configured* until a termbase was ticked for the current project, and a termbase ticked during a memoQ session gave no hits until memoQ was restarted. ### What you get **In the grid.** Matched terms are highlighted in the source segment in blue – darker for the project termbase, lighter for the others, so a project term is recognisable at a glance. A forbidden term gets a warning tint instead. **In Translation results.** Each match is an entry showing the target term, the source term it matched, and which termbase answered – *Supervertaler · BEIJER*, or *· project termbase*. A forbidden term shows its wording struck through under *Do not use*, in black, which is what black means in memoQ. **In the prompt.** From the termbases ticked AI only: approved terms are sent as the client’s preferred wording, forbidden terms as absolute constraints. While an AutoPrompt-drafted prompt is selected, only the forbidden terms travel – the prompt’s own locked table is the authority. See [A drafted prompt is the only source of terminology](/memoq/prompt-editor/#a-drafted-prompt-is-the-only-source-of-terminology). **In the context bar.** The prompt editor’s **Termbases** row summarises the selection – *BRANTS (project) + BEIJER · 1 of 2 to the model* – and opens the window when clicked. **For Claude, if you use the [MCP server](/memoq/mcp-server/).** Every row your cursor lands on is looked up by this plugin whatever MT engine is selected, and Supervertaler remembers each one – so a document you pre-translated with Google or from TM alone still becomes visible to Claude as you walk through it. Claude can look terms up, and add a term straight into the project termbase: *“we agreed* draagarm *=* support arm *– add it”*. ### Adding a term without leaving the grid Select a word, press **Alt+Up**, select its translation, press **Alt+Up** again. A small dialog opens with both halves filled in, a Forbidden tick and a note, naming the project termbase it is going into. Press **Add**, and the term is in the termbase at once – and in Supervertaler for Trados and Workbench with it. It shows in the grid and the pane the next time you move onto the segment: memoQ asks a terminology plugin about a segment once and keeps the answer, and gives a plugin no way to say the answer has changed. The dialog is your confirmation that it went in. It is the same key Supervertaler for Trados uses for the same thing, and it does not mind which order you work in: a word selected in the target cell is recognised as the translation, so you may catch the English first and the Dutch after. After the first press a small note by the cursor shows what was caught and asks for the other half; it takes the focus from nothing, so you can carry on selecting. A second press on the same side replaces that half rather than pairing a word with itself. The shortcut is live only while memoQ is the window in front. Everywhere else – Explorer, where Alt+Up is the parent folder – it is the key it has always been. Switch it off in the [prompt editor](/memoq/prompt-editor/) under **Settings → Alt+Up adds a term in memoQ**, which takes effect at once; the same tick is in memoQ’s own Supervertaler settings dialog. If the pair is left half-finished it is forgotten after two minutes, and changing project drops it too, so a word caught in one job can never be written to another job’s termbase. **The other way in.** memoQ’s own **Add Term** button on the ribbon, and its Ctrl+E shortcut, work with memoQ’s term bases only – a terminology plugin is not among the choices they offer. The one door memoQ opens for a plugin is in the Translation results pane: select both words, right-click any Supervertaler hit, and choose **Add Selection As Alternative**. It ends in the same dialog and the same termbase. The hit you right-click is only the way in; what is added is what you selected. If the project termbase runs the other way round from your project, the pair is turned to fit it. Nothing ticked Project? The dialog says so and where to fix it, rather than guessing at a background termbase. ### Preferred, not mandatory Approved terms are given to the model as a strong steer it may override when an entry is clearly wrong for the sentence at hand. That asymmetry is deliberate, and it comes from a real failure. A technical termbase may quite correctly render *applications* as *aanvragen* – in the sense of a filed application. Told to use terminology verbatim, the model translated “Mashup applications” as “Mashup-aanvragen”, which is nonsense. A translator treats a termbase as guidance they may set aside with reason, and the model is asked to do the same. **Forbidden terms are not softened.** They are stated as absolute, because that is what a forbidden term is for. ### Matching Matching respects word boundaries, so `wire` does not match inside `wireless`. Where two entries could both match, the longer wins and the shorter one inside it is suppressed: `electric module` beats a bare `module`. Matching ignores case unless the termbase is ticked CS. A termbase stored the other way round from your project – English → Dutch on a Dutch → English job – is read backwards, so its terms are found all the same. Very short entries are worth avoiding in a termbase you tick Read: a two-letter term fires on almost every segment and crowds out the terms that matter. A termbase of 12,000 terms loads in well under a second and adds under a millisecond to each lookup. ### Formats See [Importing and exporting termbases](/memoq/glossary-format/). # Troubleshooting ### Supervertaler does not appear at all Installing is not enough on its own: memoQ uses a new add-in only once it is switched on – see [Switching it on in memoQ](/memoq/installation/#switching-it-on-in-memoq). Check too that you answered **Yes** to the unsigned-plugin prompt on startup – its default button is *No*. If memoQ was recently upgraded to a new major version, it installed into a new program folder without the add-ins. Run the Supervertaler installer again; it installs into every memoQ it finds, from memoQ 11 up. See [Installation](/memoq/installation/#after-a-memoq-upgrade). ### A row was left empty with “Supervertaler left this segment for you” The model’s reply for that row contained something other than the translation – a note, an explanation, markdown – and did again when asked a second time, so it was not written into your document. The message under the row quotes what the model sent; if the translation part is sound, copy it in and delete the rest. See [What the model may send back](/memoq/prompt-editor/#what-the-model-may-send-back). If it happens often with one prompt, the prompt is probably asking for explanations. Look for lines like “add a brief explanation” and replace them with an instruction to use a `[[TC: …]]` marker. The check looks for signs of commentary that the source itself does not have, so text written in the first person is translated as usual: *Ik verklaar dat ik dit document heb vertaald* can become *I declare that I have translated this document*, because the source has its own word for “I” and the translation adds no sentence to it. One case can still be refused wrongly: a source that leaves the pronoun out, as Spanish and Italian can (*He traducido…*, *Ho tradotto…*), translated into English. If a row like that is left empty, translate it by hand. ### ”AI translation is paused” The free trial has ended, or a licensed computer has not been online for 30 days. Terminology, termbases, prompts and memory banks keep working meanwhile. Open **Supervertaler for memoQ** from the Start menu and choose **Help → Licence**: enter a key, or click **Check now** once you are online. See [Licensing](/memoq/licensing/#when-a-licence-lapses). ### It translates, but never learns **Self-learning MT** is not set. Resource console → MT settings → your resource → **Settings** tab → **Self-learning MT** → *Supervertaler*, then restart memoQ. Advertising the capability only makes the engine eligible; memoQ does not send confirmations until it is actually selected there. ### Terminology is not showing Three things must all be true: 1. **Perform terminology plugin lookups while working in the translation grid** is ticked, under **Options → Terminology plugins** 2. **Enable plugin** is ticked for **Supervertaler terms**, in the same place 3. At least one termbase is ticked Read for the project in the [Termbases window](/memoq/terminology/#the-termbases-window) In v0.1.10 and earlier, *Supervertaler terms* also read *Not configured* until a termbase was ticked for the project, and a termbase ticked while memoQ was open gave no hits until memoQ was restarted. Restart memoQ, or update. ### A termbase gives no hits Check its languages in the Termbases window. A termbase stored the other way round from the project is turned automatically, but one in an unrelated pair – German → English on a Dutch job – is read as stored and simply matches nothing. Then check the Read tick is set for *this* project: the window names the project it applies to at the top, and in a new project the ticks are filed against it only after memoQ has sent a first segment. ### An imported file produced no terms Almost always the delimiter: a file whose header row uses tabs but whose rows use spaces, or the reverse. Open it with whitespace visible. The import dialog reports how many rows it read; if that is zero the file is being read as one column. ### The panel names the wrong project, or nothing reaches the model Supervertaler learns which project is open from two channels: a translation request from memoQ, and the [live document link](/memoq/mcp-server/#the-live-document-link), which reports every document memoQ shows. With the link connected, the panel follows within a couple of seconds of your clicking into a segment of the new project. Without it, the plugin has only translation requests – an add-in cannot ask – so until the first request of a session the panel still names the last project memoQ *did* ask about, and a memory bank chosen at that moment is recorded against that earlier project. **Click the project name** in the panel (or **memoQ → Sync with memoQ now**) to take the project from the document memoQ is showing this instant. If it cannot, it says why: the live link is not connected, memoQ has not reported a document yet, or no project folder holds that document. Where Supervertaler looks is memoQ’s own answer – the custom folder set under **Options → Locations → Projects**, the default `C:\Users\\Documents\My memoQ projects` when none is set, and memoQ’s register of every project, which names each one’s actual folder – so moving your projects folder needs no setting here, and projects left behind in the old location are still found. If clicking into a segment does not update the panel, memoQ is not calling the engine at all. Open **Project home → Settings → MT settings** and look for the line **“MT plugins are currently disabled.”** A project checked out from a memoQ server can have MT plugins switched off by the project manager, and there is no client-side setting that overrides it. The terminology provider still works in such a project, because it is not an MT plugin; translation through Supervertaler does not, in any mode, and neither does staging from Claude Desktop, which enters the grid through the same engine. Ask the project manager to allow MT plugins, or take the document out through a bilingual export. If you chose a memory bank while the panel was stale, open the bank chooser again once the right project is shown – that records the choice against the right project – and check the previous project’s row in `C:\Users\\AppData\Local\Supervertaler.memoQ\memory-bank-projects.txt`, one project GUID per line, in case it now names a bank it should not. ### The log The **Activity** window in the prompt editor (**memoQ → Activity**, or Ctrl+L) shows the same log live. On disk it is: ```plaintext C:\Users\\AppData\Local\Supervertaler.memoQ\plugin.log ``` with a fallback at `C:\Users\\AppData\Local\Temp\Supervertaler-memoQ.log` if that folder cannot be written. It records what memoQ asked for and what was sent – segment sizes, how many terms matched, how many remembered segments were used, and any errors. It does not contain the text of your translations. A typical healthy line: ```plaintext translate: 199 src chars, 0 tag(s) -> 239 target chars, 0 tag(s) | recall: used 2 of 7 held | terms: 7 ``` meaning: a 199-character segment; two remembered segments and seven terms sent with it; a 239-character translation returned.