Skip to main content
Chat is the surface most users live in: ask a question in plain language, get a streamed answer grounded in your organisation’s extracted knowledge, with citations on every claim. It’s the difference between “search returned 12 rules” and “here’s how deal approval works here, and here’s the evidence.” Chat is not a vector-search wrapper around a language model. Answers are assembled from the full hybrid query pipeline over knowledge that was extracted, structured, versioned, and human-reviewed before the conversation started. The model writes the prose; the knowledge layer supplies the facts.

​
How an answer is produced

  1. The message runs through the full query pipeline: the same signals, fusion, and reranking as the API.
  2. The model generates an answer bounded by the retrieved knowledge, not by its general training. Seyn’s value is your organisation’s knowledge, not the model’s opinions.
  3. The response streams token by token, with citations linking each claim to the rules it came from. From a citation, the provenance chain continues down to raw source records.
  4. The conversation persists as a thread; history is browsable and resumable.

​
Grounding and honesty

  • Citations are not decoration. Every substantive claim carries them, and a citation resolves to a real rule, which resolves to real evidence. An answer you can’t drill into is an answer you shouldn’t trust.
  • The query bounds the generation. If the knowledge library doesn’t contain the answer, the assistant says so rather than improvising. The failure mode is “I don’t have that,” not confident fiction.
  • Review status flows through. Answers built on unreviewed (inferred) rules are still answers, but the citations show their status, so a careful reader can weigh them.

​
Operational details

AspectBehaviour
Rate limit50 messages/hour per user
PersistenceThreads and messages stored per organisation, with citation records
AccessAll roles; chat is the default member surface

​
Common mistakes

SymptomCauseFix
”I don’t have information about that” for something you know is in the source dataData was ingested but no extraction run has put it into the active libraryWalk the debugging order
Answers cite rules a human already rejectedThe active library version predates the reviewRe-run extraction; check citation review statuses
Re-asking the same question gives differently-worded answersGeneration is non-deterministic; the citations should stay stable even when prose variesJudge consistency by citations, not phrasing
Treating chat as a calculator or live-data query toolChat answers from extracted knowledge, not by querying source systems in real timeUse pattern metrics or your BI stack for live aggregates

Query

The pipeline that decides what chat gets to see.

MCP Server

The same grounded knowledge, for your own agents.