> For the complete documentation index, see [llms.txt](https://mozarkdocs.gitbook.io/appx_documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://mozarkdocs.gitbook.io/appx_documentation/agent-workspace-documentation/planner-agent/overview.md).
# Overview
## Planner Agent
Planner Agent helps you build a test plan from the test cases already in your project.
Use it to find the most relevant existing coverage for a feature, release area, or user journey, then add the selected test cases to a new or existing plan.
### Before you start
Your project must already contain test cases.
Planner Agent searches your current project and uses the test cases it finds to build the plan.
### Open Planner Agent
Open **Test Plans** from the sidebar.
In the top-right toolbar, click **✦ AI Planner**.
A drawer opens from the right side of the page. The drawer header shows **Test Plan Agent**.
### Find relevant test cases
In the chat input, describe the feature, flow, release scope, or area you want to cover.
Examples include `Payment checkout flow`, `UPI payments`, or `Login`.
When you send the request, Planner Agent searches your repository and returns the most relevant test cases.
The results appear as selectable test case cards.
### Set the number of results
Use the result limit control next to the send button to choose how many test cases Planner Agent should return.
The default is **20**.
Increase or reduce the limit before sending a new search if you want a broader or narrower result set.
### Review the results
Planner Agent returns matching test cases as cards with titles and checkboxes.
Selected test cases are checked by default so you can move quickly into plan creation.
If you want more detail, click any test case card to open its full detail view.
### Open and edit a test case
Click any result card to open the detail panel.
From there, you can review:
* title
* description
* preconditions
* test steps
* supporting metadata
Use **Edit** to update the test case before you add it to a plan.
### Create a new test plan
After reviewing the results, keep the test cases you want selected.
Then click **Create new plan**.
In the plan creation window, enter the required details such as name, status, and version.
When you save, the new plan is created with the selected test cases already linked.
### Add test cases to an existing plan
If you already have a plan, click **Add to existing plan** instead.
Search for the plan by name, select it, and confirm.
Planner Agent adds the selected test cases to that plan.
### Resume previous work
Use **Past Sessions** in the drawer header to reopen earlier conversations.
Select a previous session to continue where you left off.
To start over, click **New Session**.
### If you do not see the results you expect
Planner Agent may return fewer results when:
* the current project does not contain relevant test cases
* the request is too broad or too vague
* the result limit is set too low
If needed, rewrite the request using a clearer feature or journey name.
### Next step
Read [Planner Agent search tips](/appx_documentation/agent-workspace-documentation/planner-agent/planner-agent-search-tips.md) to learn how Planner Agent interprets queries, expands related terms, and handles empty results.
---
# 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://mozarkdocs.gitbook.io/appx_documentation/agent-workspace-documentation/planner-agent/overview.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.