> For the complete documentation index, see [llms.txt](https://doc.dastra.eu/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.dastra.eu/en/dastra-ai/ai-assistant/agents/inbox.md).

# Tracking runs

Find the history of your agent runs, their status and the detail of what they did

The **Inbox** gathers the run history of your agents: what was started, by what, when, and with what outcome.

You will find it in **Automation** > **Dastra AI** > **Inbox**.

<figure><img src="https://2697025545-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LvBxs22wUMicv9uWp6C-1972196547%2Fuploads%2Fgit-blob-566c039ed878b1d77640b23488a7cb04d3c1cfd8%2Fai-agents-inbox.png?alt=media" alt="Inbox listing agent runs"><figcaption><p>The Inbox, with the status and the source of every run</p></figcaption></figure>

Each row shows the **session**, its **status**, its **source** (Manual, Schedule or Workflow), the **start** time and the **completion** time. The selector at the top of the list narrows the view to a single agent.

Runs in progress update live: there is no need to refresh the page.

***

### The detail of a run

Click a row to open the detail. It has two tabs:

* **Conversation**: the full trace: the agent's reasoning, the tools it called, and its final answer.
* **Inputs**: the values of the input fields the run was launched with.

<figure><img src="https://2697025545-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LvBxs22wUMicv9uWp6C-1972196547%2Fuploads%2Fgit-blob-b3888561c2df04f38c4170160aaedc16e95902f0%2Fai-agents-inbox-detail.png?alt=media" alt="Detail of an agent run"><figcaption><p>The detail of a run</p></figcaption></figure>

The **Continue in chat** button carries the result of the run into a new conversation. It is the simplest way to dig into a result, ask for a rewrite, or have something corrected.

***

### Statuses

Some statuses are technical. The others come from a closing review: once the agent has written its final report, Dastra reads that report alone and picks the status that describes what it says happened. They are conclusions, not failures.

| Status                      | Meaning                                                                              |
| --------------------------- | ------------------------------------------------------------------------------------ |
| **Running**                 | The run is in progress                                                               |
| **Completed**               | The agent went all the way through its mission                                       |
| **Failed**                  | A technical error interrupted the run; the error message is shown in the detail      |
| **Human review required**   | The agent did its job but considers that a validation is needed before going further |
| **Insufficient permission** | The agent lacked the rights to reach some data or perform an action                  |
| **Feature required**        | A feature it needed is not included in the organization's plan                       |
| **Missing information**     | The available data did not allow the mission to be completed                         |
| **Incomplete execution**    | The agent hit the tool iteration limit before concluding                             |
| **Context limit reached**   | The conversation became too long for the model                                       |

{% hint style="info" %}
A **Missing information** or **Human review required** status usually points back to the agent's instruction or its list of tools: it did what it could with what it was given. The run detail generally explains what it was missing.
{% endhint %}

***

### Notifications

If you are one of an agent's **notified users**, you receive a Dastra notification at the end of every run. It tells whether the run completed (**Completed** or **Human review required**) or not. This is the recommended way to keep an eye on a scheduled agent without opening the Inbox. When you start a run yourself, the **Open Dastra AI** button also tells you when it has finished.

### Technical log

For organization-level monitoring (model used, duration, user behind the call) see the **Logs (90 days)** tab of the **AI usage** card, in **Organization settings** > **Dastra AI**. They show the last 90 days.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://doc.dastra.eu/en/dastra-ai/ai-assistant/agents/inbox.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
