> For the complete documentation index, see [llms.txt](https://docs.mozark.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mozark.ai/mcp/mozark-mcp-docs/guides/build-your-knowledge-base.md).

# Build your knowledge base

Ground AI-generated tests in product screenshots and requirements.

The knowledge base makes AI-generated test cases specific to your product. It holds indexed **app screenshots** and **requirement documents** that the Author Agent retrieves before writing anything.

## What to upload

| Content                                       | Why it helps                                                        |
| --------------------------------------------- | ------------------------------------------------------------------- |
| Screenshots of each screen in a flow          | The agent learns real labels, buttons, field names, and navigation. |
| PRDs, BRDs, user stories, acceptance criteria | Business rules, validations, and edge cases come from here.         |

## Uploading screenshots

> *"Add these three screenshots of the checkout flow to the knowledge base."*

Behind the scenes, the assistant requests a signed upload URL (`get_image_upload_url`), uploads the file, then analyses and indexes it (`process_uploaded_image`). Each screenshot is turned into a **Page Object Model (POM)**—a structured description of the screen's elements—which you can view or refine later.

## Uploading documents

> *"Upload this PRD for the loyalty programme."*

Tool: `upload_document`.

## Browsing what's indexed

> *"What screens do we have for the Payments app?"*
>
> *"Show me the POM for the cart screen."*

Tools: `list_available_screens` · `list_images` · `load_pom` · `list_pom_results` · `update_pom` · `retrieve_from_knowledge_base`.

## Keeping search fresh

Test cases are embedded for semantic search when saved. If you have older cases created before vector search was enabled, ask:

> *"Re-index all test cases in this project for search."*

Tool: `embed_test_cases`.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.mozark.ai/mcp/mozark-mcp-docs/guides/build-your-knowledge-base.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.