Back to home
Function · Knowledge
Artellis builds a tool that answers from your own wiki and links the source: answered once, for good.
The pain
Why this one is worth fixing
Your team asks the same question every week. The answer is buried in a doc somewhere. So the same person types it out again, or worse, someone guesses, and the wrong answer becomes the accepted one.
What Artellis builds
A trusted answer layer that reads your own wiki and policies, answers in your voice and links the source. Answered once, for good.
How it works
- 01Indexes your own docsWiki, policies, SharePoint, the ‘lessons learned’ file, with permissions respected.
- 02Answers with the sourceEvery answer links back to the doc it came from. No invented facts, no hallucinations.
- 03Promotes good answers to FAQRepeated questions become published FAQ entries the whole team can rely on.
Example artefact
What the output actually looks like.
Q: What is our current refund policy?
Grounded in Refund Policy v4 · 12 May 2025
Refunds within 14 days of purchase, no questions asked.
Between 14–30 days: refund at manager discretion, minus a €10 processing fee.
After 30 days: credit note only.
Source: Refund Policy v4 · /wiki/policies/refunds
You edit and send.
Where it plugs in
Notion / Confluence / SharePointGoogle DriveSlack / TeamsYour existing wiki
Guardrails
- Human-in-the-loop: nothing sends, signs or spends without you approving it.
- Your data stays yours, hosted in your tenant or a dedicated Artellis workspace, never used to train public models.
- Week-one build: something small and useful is live in the first week, before we scope anything bigger.
FAQ
How long until we see something working?
A first working version of the knowledge tool inside week one. Refinement and rollout happen after you have seen it work against your real inputs.
What do you need from us to start?
About 45 minutes to walk through the current flow, sample inputs (emails, files, screenshots, whatever you actually work from) and one person on your side who owns the outcome.
What happens if the AI gets it wrong?
Every draft goes to a human before it leaves the building. When you correct it, the tool learns your standard so the next one lands closer to right.
Bring us this workflow
One workflow. One week. Something working.