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
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.
Last updated
Was this helpful?