How it works

How answers are made (and why they can be trusted)

When someone asks a question, the assistant does not simply look up similar text and paraphrase it. It works the question properly against the knowledge base — restricted, at every step, to documents the asker is allowed to read.

1. Access first: the asker's groups, personal grants and email grants decide what is visible before anything else happens. A document the person may not read is simply not part of their knowledge base — for any question, ever.
2. The question is read the way a colleague would read it — who is asking, what they work on, and any dates it mentions all count.
3. If what comes back isn't enough to answer responsibly, the assistant keeps working: it rereads the question from other angles, opens full documents when an excerpt isn't enough (contracts, agreements), and gathers everything about an entity or a period for timeline and “all of the …” questions.
4. It writes the answer with numbered citations [1], [2] … — each number pointing at a specific passage it was actually shown.
5. Every claim is checked against its citation before the answer is shown. A claim that cannot be backed does not survive; if nothing survives, the user gets an honest “I don't have that in the knowledge base” instead of a confident guess.

Rules the assistant answers by

• Evidence has rank: a signed instrument beats a report, a final report beats meeting notes, and everything beats drafts and stale copies. Between comparable documents, the newer governs.
• Dates are computed, not guessed: deadlines, renewal windows, “the latest version” and “as of March” resolve against the documents' own dates, exactly.
• Premises get corrected: if the question asserts something the documents contradict, the answer says so explicitly.
• It answers in the asker's language, whatever language the documents are in.

A worked example

Ask “can this contract be renewed on the same terms?” and suppose the knowledge base holds a signed 2024 master agreement, a 2025 amendment changing the payment terms, and an internal Slack thread where someone speculated about renewal. The assistant weighs the amendment over the original clause it changed (evidence has rank), ignores the speculation in chat (not a governing document), and answers directly: the terms carry over except payment terms, which the 2025 amendment changed — with [1] pointing at the amendment's clause and [2] at the original agreement's renewal clause. If the amendment or the original had never been ingested, the answer would say the renewal terms aren't in the knowledge base rather than assume the original still applies.

What users see

Under each answer: the numbered sources. Clicking one opens the exact passage, so anyone can verify any claim in seconds. Follow-up questions continue the same conversation — the assistant remembers the thread and re-checks it against the documents rather than trusting its own memory. Asking “and what about the SLA?” right after works the way it would with a colleague: it knows which contract you are still talking about.

Last updated 20 Sep 2026