# Instructions

> Define what an agent does, in named blocks you can revise independently.

Source: https://docs.runbear.io/agents/instructions

Last updated: 2026-08-26

Instructions are the agent's behavior in your own words: what it is for, who it
serves, how it should answer, and what it must not do. They are sent with every
request, so they apply to every channel the agent is deployed to.

## Named blocks, not one long page

An agent's instructions are stored as separate blocks, each with a name. Give
each block one subject: the agent's role, the tone to use, an escalation rule, a
list of team-specific terms.

Blocks are easier to revise than a single page, and the name tells you where to
look when the agent gets something wrong. A support agent might carry
`Role`, `Tone`, `When to escalate`, and `Product vocabulary`.

## Writing instructions that hold up

State what the agent should do when it does not know. Without that rule an agent
fills gaps with plausible text.

> If the handbook does not cover the question, say so and point the user to the
> People team. Do not infer policy.

Name the audience. "Answer employees" and "answer customers" produce different
levels of internal detail from the same knowledge base.

Say what to leave out. Agents default to thorough; most channels reward brevity.

Keep facts that change out of instructions. Prices, staffing, and policies belong
in [knowledge](/agents/knowledge/overview.md), where they update on sync instead of
requiring an edit here.

## Improve with chat

The Instructions tab has an **Improve with chat** panel. Describe the behavior you
want in plain language and it proposes edits to the blocks, which you review
before they are saved.

This is the fastest way to act on a bad answer: paste the answer, say what it
should have been, and apply the proposed change.

## Related

- [Testing and improving](/agents/testing.md) — try changes before they reach users
- [Knowledge](/agents/knowledge/overview.md) — facts the agent looks up rather than memorizes
- [Agent settings](/agents/settings.md) — model, reasoning effort, and access