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

# Agent instructions

> Tell your agents how to behave. Standing guidance that shapes every response.

Instructions are standing guidance you write for an agent. They shape how the agent responds, what it prioritizes, and what it avoids, every time it's tagged in a thread.

Think of instructions as a standing brief: the context a good employee would have read before they started.

## Where instructions live

**Global instructions** apply to the agent everywhere, in every Space it's added to.

**Space-specific instructions** apply to the agent only in a particular Space, and override the global instructions where they conflict.

## What to include in instructions

Good instructions cover:

* **Role**: what this agent is responsible for in this context
* **Tone**: how it should sound (formal, direct, casual, technical)
* **Format preferences**: bullet points, prose, tables, short or long responses
* **What to prioritize**: which tools, which decisions, which context to lean on
* **What to avoid**: topics outside its scope, assumptions it shouldn't make
* **Recurring context**: information it should always have in mind

## Example instructions

**For a marketing agent in a specific client Space:**

```
You support the Acme Corp account's marketing work. Always reference the Acme brand guide (pinned) before drafting copy. Write in a professional but approachable tone, not casual, not formal. Keep deliverables short and action-oriented. Flag anything that contradicts the approved messaging framework.
```

**For a support agent:**

```
You summarize support threads and surface recurring issues for the team. When asked about a customer issue, cite the thread and ticket number. Never speculate about root causes without data. Keep summaries to three bullet points unless asked for more.
```

## Tips for writing good instructions

* **Be specific.** "Be helpful" is not an instruction. "Respond in bullet points and keep each point under 15 words" is.
* **State constraints clearly.** If there are topics or actions outside scope, say so explicitly.
* **Update them when the work changes.** Stale instructions lead to misaligned responses.
* **Test with real questions.** Write an instruction, tag the agent with a real question, and see if the output matches your expectations.

<Tip>
  Write instructions as if you're onboarding a new team member to a specific role. What would they need to know on day one?
</Tip>

## Character limit

Instructions are capped at 2,000 characters per instruction set (global and per-Space). Keep them tight. If you find yourself writing more, split the context into pinned docs the agent can read instead.

## Related

* [Pins](/spaces/pins) for pinning context the agent should always have
* [Create an agent](/agents/create-an-agent)
* [Custom agents](/agents/custom-agents)


## Related topics

- [The default agent](/docs/agents/default-agent.md)
- [Create an agent](/docs/agents/create-an-agent.md)
- [Agent permissions](/docs/agents/agent-permissions.md)
- [Custom agents](/docs/agents/custom-agents.md)
- [Copywriting](/docs/teams/marketing/copywriting.md)