> 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/best-practices.md). # Best practices ## Best practices ### Describe features naturally Use the language your team uses in the app or workflow under test. A clear request such as `Verify UPI payment flow including VPA entry and PIN` works better than a short keyword list. ### Keep each request focused Search or generate for one feature, journey, or release area at a time. Focused requests are easier to review and usually return better results. ### Start cleanup with Semantic mode Use **Semantic** mode first when you want to find both exact duplicates and near-duplicates. Use **Exact** mode when you want to confirm direct copies. ### Scan large repositories in smaller scopes For large repositories, run **Cleaner Agent** one journey at a time. This makes the results easier to review and act on. ### Review before you delete or merge Treat recommendations as a starting point. Before you delete a test case, confirm that any unique detail has been preserved. ### Add Knowledge Base sources for better authoring [Author Agent](/appx_documentation/agent-workspace-documentation/author-agent/overview.md) works best when your project includes relevant Knowledge Base sources. Add requirements, flows, or supporting documents if you want more accurate generated coverage. ### Reuse sessions deliberately Use one session for one task when possible. This keeps your planning, cleanup, and authoring history easier to revisit later. ### Check the current project before you start All agent results are scoped to the project you selected at the top of Test Case Manager. If results look incomplete, confirm that you are working in the intended project. --- # 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/best-practices.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.