> ## Documentation Index
> Fetch the complete documentation index at: https://docs.custral.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Instructions

> How to write the system-prompt text for a chat agent.

Agent instructions are free-form text that gets prepended to the conversation's system prompt. There's no length limit, but the model still has a context window. Keep instructions tight.

## Anatomy of a good agent prompt

<Steps>
  <Step title="Persona, who is the agent">
    One sentence: "You are the Product Agent for Custral, focused on product strategy and feedback."
  </Step>

  <Step title="Voice. How should it speak">
    Two or three lines. Examples: "Be concise. Use bullet points for any list of three or more. Don't apologize."
  </Step>

  <Step title="Constraints. What it must not do">
    "Never write directly to the database. Always confirm a destructive change with the user first."
  </Step>

  <Step title="Procedures, repeatable patterns">
    Step lists for common asks. "When the user asks for a feature summary, fetch the feature record, list its open conversations, and produce a one-paragraph summary tied to revenue impact."
  </Step>
</Steps>

## What instructions do not control

* Available tools. Set with the agent's allowed-tools list and web-access toggle, not in prose.
* Scope. Set with the agent's scoped objects and pages. A prompt instruction that says "only read the deals object" is unreliable; use the scope settings instead.
* Model choice. Set with the agent's model setting, not in prose.


## Related topics

- [Workspace General Settings](/start/onboarding/workspace.md)
- [Rules & Skills](/ai/rules-and-skills.md)
- [Chat Agents](/ai/chat-agents/overview.md)
- [Settings](/start/settings/overview.md)
- [AI](/ai/overview.md)