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

# Logs

> Every LLM call and agent task, with the columns and tabs on the page

|             |                                             |
| ----------- | ------------------------------------------- |
| **URL**     | `/logs`                                     |
| **Sidebar** | Logs                                        |
| **Roles**   | Admin · Manager · Analytics Viewer · Member |

Logs is the record of every request your agents made through Unbound — the prompt, the model, the tokens and the outcome.

## What's on the page

### Tabs

| Tab          | `?tab=` | Contents                                 |
| ------------ | ------- | ---------------------------------------- |
| **All Logs** | `logs`  | Every LLM call                           |
| **Tasks**    | `tasks` | Agent tasks — Admin and Analytics Viewer |

The **Tasks** tab only appears for Admin and Analytics Viewer. A `?tab=tasks` link opened by anyone else lands on **All Logs**.

### All Logs

| Column            | Contents                        |
| ----------------- | ------------------------------- |
| **Timestamp**     | When the request was made       |
| **User**          | The developer it ran as         |
| **Tool Type**     | The AI tool that made it        |
| **Prompt**        | The prompt, cleaned for display |
| **Model**         | The model that answered         |
| **Input Tokens**  | Tokens sent                     |
| **Output Tokens** | Tokens returned                 |
| **Status Code**   | The response status             |

### Tasks

| Column        | Contents                                                                 |
| ------------- | ------------------------------------------------------------------------ |
| **Timestamp** | When the task began                                                      |
| **User**      | The developer who asked                                                  |
| **Task**      | What was asked for                                                       |
| **Cost**      | Estimated cost of the task                                               |
| **Tool Type** | The AI tool that ran it                                                  |
| **Models**    | The models involved                                                      |
| **Actions**   | What the agent did, as icons — the first three, then a `+n` for the rest |

## Filters and controls

Both tabs carry a search box, faceted filters and a time range. **All Logs** filters by tool type, user, model and status; **Tasks** filters by tool type, user and model. The time range defaults to the last 24 hours, takes a custom range, and is remembered between visits.

Each tab also has a column picker for hiding columns you do not need, and columns can be dragged wider.

## What you can do

| Action         | Result                                                                                                                                                                                                                              |
| -------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Select a log   | Opens its detail, and puts `?log_id=` in the URL so the open log can be shared or reopened in a new tab                                                                                                                             |
| Select a task  | Opens its full trace at `/logs/tasks/[thread_id]`                                                                                                                                                                                   |
| **Export CSV** | Opens a confirmation showing the time range and the filters that will be covered. Confirming starts the export — the button reads **Exporting…**, then **Download**. Offered to an Admin or an Analytics Viewer, and to nobody else |

### Task trace

The trace opens on **Interaction Breakdown**, the task's turns in order with the total cost for the task. Each turn expands into the request, the reply and the tools the agent reached for. **Summarize** writes a summary of the whole task on request — it is offered to an **Admin** or **Manager**, not to an Analytics Viewer — and the search box narrows the turns by model or prompt.

## Common questions

**How do I export logs?**
Export from the table controls — the CSV covers your current filters and time range. Exports are available to Admin and Analytics Viewer.

**Where do I see what an agent actually did, rather than what it was asked?**
[Analytics — Agentic Use](/dashboard/analytics/agentic-use), which classifies each command and tool call and matches it against your policies.

**How do I see a whole task from start to finish?**
The **Tasks** tab, then select a task for its turn-by-turn trace.

## Related

| Page                                                        | For                                                                                        |
| ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
| [Analytics — Agentic Use](/dashboard/analytics/agentic-use) | What agents *did* — commands, tool calls and skills, classified and matched against policy |
| [Analytics — Tasks](/dashboard/analytics/tasks)             | Tasks with work type, repository and spend                                                 |