> ## 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.

# Best Practices

> How to get reliable, predictable output from agents.

A few patterns that consistently improve agent quality across both chat and property auto-fill.

<Steps>
  <Step title="Be specific about output shape">
    "Reply in one sentence" beats "be brief". For property agents, say "Return a single value from this list: A, B, C". The closer the prompt is to the coerced shape, the higher the success rate.
  </Step>

  <Step title="Focus and gate aggressively">
    A chat agent given a tight focus (scoped objects and pages) and a short list of allowed tools behaves more like a focused subject-matter expert than an unscoped general assistant. Scope is a soft hint (it biases the agent toward the right data rather than hard-blocking it) but fewer tools means fewer wrong turns.
  </Step>

  <Step title="Test on real records before relying on triggers">
    For property agents, run on five representative records manually before turning on automatic triggers (on create, on update). Verify the run trace, not just the written value.
  </Step>

  <Step title="Pick the right tier">
    Fast models (Claude Haiku 4.5, GPT-4o mini) are right for high-volume property auto-fill. Reasoning models (Claude Opus 4.7, o1-mini) are right for schema design and complex chat. Balanced models (GPT-4o, Claude Sonnet 4.6) are the safe default.
  </Step>

  <Step title="Watch the run trace">
    The property agent run panel shows what the AI produced and the value that was written. When something goes wrong, read the trace before tweaking the prompt blindly.
  </Step>
</Steps>


## Related topics

- [Conversation Widget](/blocks/widgets/conversation.md)
- [Property Lists](/blocks/embedded/object/property-list.md)
- [Getting Started](/data/getting-started.md)
- [Permissions Overview](/team/permissions/overview.md)