> For the complete documentation index, see [llms.txt](https://docs.wonderchat.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.wonderchat.io/setup-guides/correcting-your-chatbot/how-to-review-your-chatbot.md).
# How to Review your Chatbot
The Review workflow helps you decide whether an unresolved conversation actually requires action, and what type of fix is most appropriate.
The goal is not to fix every unresolved chat.
The goal is to identify real issues while keeping the Review inbox clean, accurate, and high-signal.
***
### Step 1: Open the Review Tab
Each unresolved chat is automatically analyzed by the AI triage system and categorized into one of four issue types:
* Knowledge Gap
* User reported
* Conflicting Info
Start by reading:
* The customer’s original question
* The chatbot’s response
* The triage classification
* Any suggested reasoning provided by the system
***
## Step 2: Reviewing Each Error
Open each case and:
* Add missing documentation
* Improve existing knowledge coverage
* Upload missing source material
***
The review system is designed to improve chatbot quality over time by helping teams focus on the right problems instead of reacting to every unresolved conversation.
---
# 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, and the optional `goal` query parameter:
```
GET https://docs.wonderchat.io/setup-guides/correcting-your-chatbot/how-to-review-your-chatbot.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.