ThalassA
About

An assistant that answers while the conversation is still running.

Thalassa listens to your conversation and writes an answer into a window only you can see — grounded in your own documents, with the source shown.

The assistant window during a live conversation — the question is heard, the answer is already written.

Thalassa follows a live conversation, notices when a question is aimed at you, and drafts an answer while the other person is still speaking. The window it writes into is excluded from screen sharing and screen recording — the people you are talking to do not see it. Before the conversation it builds a briefing from your own documents. Afterwards it writes a report: what was decided, which objections came up, what to follow up on.
Documents are read, indexed and searched locally; only the passages that match a question travel with the request. One exception at ingest, which we would rather name than have you discover: a scanned PDF contains pictures of text, so each page is sent to our backend in Frankfurt once, to be turned into text. It happens when you add the file, never during a conversation, and it can be switched off. Conversations are not stored. Live translation is optional and sends the other side's speech to DeepL while the meeting runs — leave it off and nothing leaves the European path (privacy policy, section 3.3b).
It does not record your meetings. It does not decide whether you are allowed to use assistance in a given setting, and it cannot know the rules that apply to you — that judgement stays yours. Where a selection process forbids aids, using it is not permitted; that stands in the terms, not just here.
Where the line runs

Three neighbouring categories get confused with this one.

Note-taking and conversation-analysis tools join the meeting as a participant or record system audio, transcribe, and store — their value arises after the conversation: summaries, a searchable archive, analysis of sales calls. A tool whose value is the archive has to store. For a client conversation nobody wants archived, that is the disqualifying property, not a feature. Thalassa answers during the conversation and keeps nothing afterwards.
Tools in the neighbouring category have caught up on the window and on working from system audio instead of joining as a bot. What actually differs is the business model behind it — no recording, no archive — and where the answer comes from: your documents first, with the source shown.
A general model answers from what it learned. It does not know your 2026 price list, your framework agreement or your case file. It answers anyway — plausibly, and wrong. Thalassa searches your documents first, shows where the answer came from, and when sources disagree, your knowledge base wins. It also hears the question itself, so nobody has to type while someone is talking to them. Said plainly: for general questions a general assistant is just as good and cheaper. The premium is worth it where your own documents are involved and where it has to happen live. Otherwise not.
There is a growing group of tools aimed openly at getting through selection procedures, advertising invisibility. The proximity is uncomfortable and we would rather name it than hope you do not: the technology overlaps, the intent does not. Thalassa does not advertise circumventing selection procedures, states the restriction in its terms, and aims product, price and language at professional conversations.
Questions people actually ask

The things worth knowing before you try it.

Who builds Thalassa?

Thalassa Consulting Kft., Budapest. Full company details are in the imprint.

Can you read my documents?

No. They are read, indexed and searched on your machine. What reaches us is the passage that matches a question, for the length of that request — plus the one named exception for scanned PDFs, which you can switch off.

Do you store my conversations?

No. There is no archive and no transcript on our side. That is not a setting; it is how the product is built — which is also why it cannot offer you a searchable history later.

Where does the backend run?

Frankfurt, Germany (AWS eu-central-1). The one path that leaves it is optional live translation via DeepL, and only while it is switched on.

Is it allowed where I want to use it?

That judgement is yours. Thalassa cannot know the rules of your employer, your client or your examination board, and it does not pretend to. Where aids are forbidden, using it is not permitted.

See it on a real conversation

Install it, point it at your own documents, and run one meeting with it. That answers more than any page can.