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

# AI Agents limits

> Limits that affect Fliqr AI Agents — included tokens, knowledge base size, context windows, and related platform caps.

Design Agents inside these limits. Account-wide numbers also appear in [Platform limits](/docs/troubleshooting/platform-limits).

## AI Agent caps

| Limit               | Value                                                    | Notes                                 |
| ------------------- | -------------------------------------------------------- | ------------------------------------- |
| Knowledge base size | **500MB** indexed content per agent                      | Split content across agents if needed |
| Agents per account  | No hard limit documented                                 | Still keep ownership clear            |
| Context window      | Model-dependent (for example GPT-4o up to \~128k tokens) | Long threads may truncate older turns |

## Included quota and BYO keys

* Pro plans may include a monthly OpenAI token allowance (see Billing / plan details in-product).
* When included quota is exhausted, Agent replies pause until the next cycle **or** you connect your own provider key — [AI Providers](/docs/core-concepts/ai-agents/ai-providers).

## Related Flow / media limits

If you mix Agents with Flows (vision, image gen, speech):

| Limit                  | Value          |
| ---------------------- | -------------- |
| Blocks per Flow        | 250            |
| Flows per account      | 100            |
| General upload ceiling | Often **25MB** |

Full tables: [Platform limits](/docs/troubleshooting/platform-limits).

## Practical guidance

* Retrieve less, answer more — prune noisy knowledge pages
* Use smaller models for high-volume FAQs
* Log tool failures; don’t retry unbounded loops in prompts
* Set budget alerts under **Settings → AI Usage** when available

## Next

<CardGroup cols={2}>
  <Card title="Best practices" icon="check" href="/docs/core-concepts/ai-agents/best-practices">
    Stay reliable inside these caps.
  </Card>

  <Card title="Platform limits" icon="gauge" href="/docs/troubleshooting/platform-limits">
    API rate limits and account quotas.
  </Card>
</CardGroup>