# Investigate blocked actions

Review why an action was stopped and decide whether policy, access, or agent behavior should change.

- Category: Operations Command Center
- Last updated: 2026-06-19
- URL: https://help.irongorilla.ai/articles/investigate-blocked-actions

## A block is a control working

Blocked actions are not noise. They are moments where policy prevented an agent from crossing a boundary. The investigation should decide whether the block was correct, the policy is too broad, or the agent needs a narrower scope. An [LLM trace](/articles/read-an-llm-trace) can help when the block involved a model call.

![Iron Gorilla operations dashboard with metrics, approval queues, and agent activity.](https://help.irongorilla.ai/help/screenshots/operations-dashboard-overview.png)

_The operations dashboard gathers active risk, approvals, and audit context in one working view._

## Investigating the block

Open the blocked action from Operations or audit history and review the agent, tool, destination, policy, and trust context together. Repeated patterns usually matter more than a single isolated block.

Adjust [policy](/articles/create-a-policy-from-plain-language) only when the business boundary was wrong or incomplete. Adjust connector or agent scope when the agent had more access than it needed.

## Related articles

- [Use the operations dashboard](https://help.irongorilla.ai/articles/use-the-operations-dashboard)
- [Simulate a policy before launch](https://help.irongorilla.ai/articles/simulate-a-policy-before-launch)
- [Read an LLM trace](https://help.irongorilla.ai/articles/read-an-llm-trace)

## Support

Need help? Tell us where you got stuck: https://help.irongorilla.ai/contact