> For the complete documentation index, see [llms.txt](https://ask.birdie.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ask.birdie.ai/agent-quality-assurance/agent.md).

# Agent

## Overview

The **Agent** page is the individual performance view in Agent Quality Assurance.

It helps supervisors understand how one agent performs across the interactions included in the selected QA context.

Use it to connect quality scores, reasons, and criteria to real coaching decisions.

<figure><img src="/files/kTw2ifGQSvKnneQ2BlBw" alt=""><figcaption></figcaption></figure>

## Why the Agent page matters

The Agent page helps teams:

* evaluate quality at the person level
* spot strengths and recurring failure patterns
* identify which Reasons or Criteria need coaching
* track improvement over time

## How agent analysis works

Birdie aggregates the interactions that match the current filters and shows how one agent performs within that scope.

This makes it easier to separate isolated issues from recurring behavior.

Agent analysis is especially useful for:

* coaching and feedback cycles
* supervisor follow-up
* calibration discussions
* performance reviews based on evidence

## Agent, Reasons, and Criteria

The Agent page connects individual performance to the QA model behind it.

Use it to understand:

* which [Reasons](/agent-quality-assurance/reasons.md) this agent handles most
* which [Criteria](/agent-quality-assurance/criteria.md) pass or fail more often
* where the agent needs support, coaching, or recognition

## Agent in analysis

The **Agent** analysis page follows the same layout described in [Analysis Page Structure](/getting-started/platform-overview.md).

What changes is the level of analysis. Instead of looking at a full Area or one Reason, you focus on one agent inside the selected scope.

## Related articles

* [Agent Feedback](/agent-quality-assurance/agent/agent-feedback.md)
* [Reasons](/agent-quality-assurance/reasons.md)
* [Criteria](/agent-quality-assurance/criteria.md)


---

# 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://ask.birdie.ai/agent-quality-assurance/agent.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.