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

# Agent integration

> How future agents should interact with FloKit actions and guardrails.

Agent integrations should treat FloKit as the controlled growth operating layer. Agents can propose, explain, approve, or monitor work only within the permissions and guardrails configured by the workspace.

## Integration pattern

```mermaid theme={null}
flowchart LR
  Agent["Agent"] --> Context["Workspace context"]
  Context --> Guardrails["Guardrails"]
  Guardrails --> Actions["Action queue"]
  Actions --> Approval["Human or policy approval"]
  Approval --> Execution["Execution"]
  Execution --> Reporting["Outcome reporting"]
  Reporting --> Agent
```

## Principles

* Read context before proposing action.
* Explain the signal behind every recommendation.
* Respect workspace guardrails before execution.
* Prefer approval-based workflows for high-impact actions.
* Record outcomes so future recommendations improve.

## Planned capabilities

* Fetch available workspaces and guardrails
* Create proposed growth actions
* Check approval status
* Read action outcome reports
* Subscribe to action and guardrail events