A real company brain — accurate, on-voice, in its lane.

A one-doc assistant is easy; a knowledge hub your team trusts is a craft. This lesson is about curation and guardrails — loading real documents, giving the assistant your voice and a never-say list, and making every answer trustworthy with citations and honest gaps.

The mental model

Scaling to a company brain is about curation and guardrails — what you feed it, and the rules you give it.

A team's knowledge hub is only as good as the documents behind it and the rules that keep it honest. The work shifts from writing instructions to curating knowledge and setting guardrails so it stays accurate, on-voice, and in its lane.

The reframeGarbage in, confident garbage out. The assistant faithfully reflects whatever you feed it — including outdated or contradictory docs. Curation is the job now.

Step 01 · Set the guardrail set

A company brain represents you, so set the rules explicitly. Switch on each guardrail:

Guardrails:

0 / 4

That's a brain that stays in its lane. Now make answers trustworthy.

Step 02 · Trustworthy answer, or not?

Trust comes from honesty, not confidence. Tap each answer — does it earn trust, or break it?

Trust promptWhen you answer, cite which document it came from. If the documents don't cover the question, say so and don't guess. If it's outside your scope ([scope]), say it's not something you can help with and point to [where].

Two traps: conflicting documents (the assistant picks one at random — keep a single source of truth per topic) and oversharing (it'll surface internal or sensitive info to anyone — control what goes in; see the Secure Your AI Use build). Knowledge rots — decide who owns updates and remove stale docs; a confidently wrong answer from a stale policy is worse than no answer.

Your challenge: build a trustworthy brain

Load several real documents as a structured knowledge base.
Add a voice guide, a do/don't, and a never-say list.
Make it cite sources and admit gaps; test the citations.
Decide who owns updates and how often.

✓

Lesson complete

You can build a structured multi-doc knowledge base, give an assistant a voice guide and guardrails, write a never-say list and escalation rules, make answers cite sources and admit gaps, and keep knowledge current.

Up next

Lesson 3 · Share it with your team — access, live data & upkeep

Continue to Lesson 3 →

Open the Playground Back to Custom AI Assistant