> For the complete documentation index, see [llms.txt](https://learn.heeler.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learn.heeler.com/tenant-admin-guide/agent-executions.md).

# Agent Executions

## Viewing Agentic Remediation History

The **Agent Executions** page is the audit trail for everything Heeler's remediation agent has done — every fix attempt, every PR opened, every run that failed or completed. Use it to see what's been tried, debug an unexpected outcome, or report on auto-fix activity over time.

### Where to find it

Open the **gear icon** in the top-right → **Agent Executions** tab. This is a flat list (no sub-sections).

URL: `https://app.heeler.com/administration/agent_executions`

### Quick start

* The page lists agent runs in reverse-chronological order by default.
* Use the **Status** filter to focus on Failed runs, or **All Filters** for finer control (by agent type, source, time range).
* Click any row to drill into the full execution detail — the agent's plan, tool calls, decisions, and final outcome (PR opened, no-op, error).

### Reference

#### Table columns

| Column           | Description                                                                         |
| ---------------- | ----------------------------------------------------------------------------------- |
| **Title**        | Short summary of what the agent was working on (typically the finding being fixed). |
| **Agent Type**   | Which agent ran (e.g., dependency-upgrade, SAST-fix).                               |
| **Initiated By** | What triggered the run — a workflow, manual trigger, or scheduled.                  |
| **Source**       | The triggering finding or remediation.                                              |
| **PR**           | Link to the pull request opened by the agent, if any.                               |
| **Status**       | Success / In Progress / Failed / No-op.                                             |
| **Created At**   | When the run started.                                                               |
| **Completed At** | When the run finished.                                                              |

#### Filters

* **Status** — quick filter chip at the top (Success / Failed / In Progress / etc.).
* **All Filters** — opens a panel where you can filter by agent type, source, time range, repository, and team.
* **Search** — free-text search over titles and identifiers.

#### Drill-down detail

Clicking into a single execution shows:

* **Plan** — what the agent decided to do.
* **Tool calls** — every shell command, file edit, and API call the agent made.
* **PR details** — the diff that was opened (or proposed).
* **Outcome** — terminal state with any error messages.

This is useful both for debugging failed runs and for compliance / audit purposes (showing exactly what an autonomous agent did).

### Visibility

* **Tenant Admins** see all agent executions in the tenant.
* **Standard Users** typically see executions related to their team's repositories; check Roles/Permissions for the current scope.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://learn.heeler.com/tenant-admin-guide/agent-executions.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.