# Analytics and Reports

The Home dashboard includes a Reports widget showing metrics for the last 7 days:

* Tickets processed
* Resolution rate
* $ Saved
* Avg CSAT

## Outputs

The **Outputs** tab in your agent workspace shows every conversation your agent has handled. Each conversation includes:

| Column              | What it shows                                                    |
| ------------------- | ---------------------------------------------------------------- |
| **Resolution**      | Whether the conversation was resolved without human intervention |
| **CSAT**            | Customer satisfaction rating (Great, Good, Fair, Poor)           |
| **Gap in training** | Whether the agent lacked knowledge to answer the question        |
| **Channel**         | Which integration or channel the conversation came from          |

### CSV export

You can export your conversation history and metrics as a CSV file. The export is generated and sent to your email.

### Using Outputs to improve your agent

**Look for gaps in training.** Filter by conversations flagged as having a gap — these show you exactly where you need to add more knowledge.

**Review low CSAT scores.** Conversations rated Fair or Poor highlight areas where your agent's responses need improvement.

**Check resolution rates.** A high resolution rate means your agent is handling conversations well. If it's low, review the escalated conversations to understand why.

## Skills

[Skills](/skills/what-are-skills.md) are a great way to use plain text instructions to explain to the agent the information it should extract in a report. Some Skills we have are:

* Support Analytics Skill
* KB Auto Updater

and more.

Simply add the skill, edit the text field instructions within the skill (like adding a time frame, and what info it should extract like "top 10 questions") and hit run.


---

# Agent Instructions: 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://docs.eesel.ai/admin/analytics-and-reports.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.