You can provide a custom system prompt to guide the Query Agent's behavior, by passing it as part of the [instantiation](instantiation.md).

:::code-group{sync="languages"}
```python title="Python"
from weaviate.agents.query import QueryAgent
from weaviate.agents.classes import QueryAgentCollectionConfig

# Define a custom system prompt to guide the agent's behavior
system_prompt = """
You are a helpful assistant that can answer questions about the products and users in the database.
When you write your response use standard markdown formatting for lists, tables, and other structures.
Emphasize key insights and provide actionable recommendations when relevant.
"""

qa = QueryAgent(
    client=client,
    collections=[
        QueryAgentCollectionConfig(
            name="ECommerce",
            target_vector=["name_description_brand_vector"],
        )
    ],
    system_prompt=system_prompt,
```

```typescript title="JavaScript/TypeScript"
import { QueryAgent } from 'weaviate-agents';

// Define a custom system prompt to guide the agent's behavior
const systemPrompt = `
You are a helpful assistant that can answer questions about the products and users in the database.
When you write your response use standard markdown formatting for lists, tables, and other structures.
Emphasize key insights and provide actionable recommendations when relevant.
`;

const qa = new QueryAgent(client, {
    systemPrompt: systemPrompt,
    collections: [
        {
            name: 'ECommerce',
            targetVector: [
                'name_description_brand_vector'
            ],
        },
    ],
});
```
:::

Then any run using the Query Agent will use this new set of instructions.

A custom system prompt is supported in **both Ask Mode and Search Mode.**

## How is it used?

The system prompt is used in two places:

1. During the query/aggregation writing - the system prompt is passed in addition to a general set of instructions to guide the construction of any queries.
2. During the writing of the final answer - the system prompt overrides a general prompt.

Therefore it is most useful to use the system prompt in one of two ways:

- Instructions specific for your data, so that the query writing agent has additional information to write queries more effectively.
- A guide for style and tone in writing the final answer, such as specific formatting instructions.

## Questions and feedback

Have a question or feedback? Here's how to reach us.

::::card-grid
:::card{title="Community Forum" href="https://forum.weaviate.io/c/support" icon="messages-square"}
Ask questions and connect with other developers on our **Community forum**.
:::

:::card{title="Support" href="/guides/support-overview" icon="life-buoy"}
Weaviate Cloud user or customer? Find the right channel on the **Support page**.
:::
::::

## Related pages

- [Agents](./agents-index.md)
- [AI-assisted Weaviate code generation](./ai-assisted-vibe-coding-index.md)
- [APIs](./apis-index.md)
- [Authorization and authentication](./authorization-and-authentication-index.md)
- [Benchmarks](./benchmarks-index.md)
- [Best practices](./best-practices-index.md)
- [Client libraries](./clients-index.md)
- [Client Libraries / SDKs](./client-libraries-index.md)
- [Cloud](./cloud-index.md)
- [Cloud account management](./cloud-account-management-index.md)

# Agent Instructions

This portal answers questions programmatically. To receive a synthesized,
source-cited answer instead of crawling page by page, append the `?ask=`
query parameter to any page URL on this site:

    /guides/quickstart?ask=how+do+I+authenticate

Optional parameters:

- `&goal=<what-you-are-trying-to-do>` steers the answer toward your
  objective (e.g. `&goal=write+a+python+client`).
- `&version=<label>` scopes the answer to a mounted version when the
  portal publishes more than one.

The response is `text/markdown`: the answer followed by a `# Sources` list
of the portal pages it was grounded in. Status codes are the contract:

- `200` — the answer; `402` — the portal owner’s plan or answer credits are
  exhausted (surface this to your operator; do NOT retry); `429` — you are
  rate-limited; back off for the `Retry-After` seconds; `503` — the answer
  lane is temporarily unavailable; fall back to crawling the `.md` pages.

For the full corpus map read `llms.txt` at the site root; for the tool
surface (search + page fetch as MCP tools) see `/mcp`.