Knowledge
Manage project knowledge and context for better AI assistance
QA.tech’s knowledge system helps AI assistants understand your project better by providing three types of context: knowledge items, global context, and auto-generated summaries.
Knowledge Items
Add documentation, links, and text content that AI assistants can reference when chatting and generating tests. This knowledge is searchable and helps provide accurate, project-specific context.
What You Can Add
- URLs: Link to documentation sites, help pages, API docs
- Text Content: Add custom instructions, project notes, or guidelines
How It’s Used
Knowledge items are automatically searched when:
- Chatting with AI assistants about your project
- Generating new test cases
- Getting project-specific help and recommendations
The AI uses semantic search to find relevant information from your knowledge base to provide accurate, context-aware responses.
Adding Knowledge Items
Navigate to Knowledge Settings
Navigate to Settings → Knowledge.
Add New Knowledge
Click “Add Knowledge” to create a new knowledge item.
Choose Content Type
Choose your content type (URL, or Text) based on what you want to add.
Fill in Details
Fill in the title and content for your knowledge item.
Save and Process
Save to process and index the content for use by AI assistants.
Global Context
Global context gets included in the AI agent’s prompt for all tests in your project. Use this to specify project-specific behaviors, requirements, or guidelines that help the agent perform better.
What to Include
The global context should contain information that the AI agent should be aware of when executing any test:
- Service Description: “The service is a route planning service for American railways”
- Data Requirements: “When creating users, always use Swedish names”
- Quality Standards: “Always fail tests when obvious typos are found”
- UI Guidelines: “If a button is red, it should never be clicked”
- Authentication Flows: “Login requires 2FA via SMS”
Best Practices
- Keep it concise but specific
- Focus on universal rules that apply to all tests
- Include domain-specific terminology and behaviors
- Mention any unusual UI patterns or interactions
For detailed examples and guidelines, see Project Context Best Practices.
Project Summary
An AI-generated summary of your website’s functionality and structure based on analysis of your pages and user interactions. This automatically provides context to help AI assistants understand your project better.
How It Works
- Page Analysis: QA.tech analyzes your website’s structure and functionality
- Graph Generation: Creates a knowledge graph of your site’s features and flows
- AI Summary: Generates a comprehensive summary using the graph data
- Automatic Updates: Refreshes as your site changes and more analysis is completed
What’s Included
The summary typically contains:
- Overview of your platform’s purpose and main functionality
- Key features and user flows
- Important pages and their purposes
- Integration points and external services
Refreshing the Summary
Navigate to Knowledge Settings
Navigate to Settings → Knowledge.
Find Project Summary
Find the “Project Summary” section on the page.
Refresh Summary
Click “Refresh” to generate an updated summary based on your latest site analysis.
The summary requires initial site analysis to be completed. If no summary appears, ensure you’ve run some tests or site analysis first.
Knowledge in Chat
When using QA.tech’s chat feature, the AI assistants automatically:
- Search Knowledge Items: Find relevant documentation and custom content
- Apply Global Context: Use project-specific guidelines and requirements
- Reference Summary: Understand your site’s overall structure and purpose
This provides more accurate, project-specific responses when asking about:
- How to test specific features
- Best practices for your type of application
- Troubleshooting test issues
- Understanding test results
Knowledge in Test Generation
When generating new tests, AI assistants use your knowledge to:
- Understand Requirements: Apply global context rules and guidelines
- Reference Documentation: Find relevant testing scenarios from your docs
- Avoid Duplicates: Check against existing test patterns
- Suggest Improvements: Recommend tests based on your documented flows
Managing Knowledge
Organization Tips
- Use Clear Titles: Make knowledge items easy to find and understand
- Keep Content Current: Regularly update documentation links
- Remove Outdated Info: Delete or update knowledge that’s no longer relevant
- Test Your Knowledge: Ask the chat assistant questions to verify knowledge quality
Troubleshooting
Knowledge not being found in chat:
- Ensure content has been fully processed (check status indicators)
- Try different search terms or questions
- Verify the content is relevant to your question
Global context not being applied:
- Check that you’ve saved the global context settings
- Verify the context applies to the type of test you’re running
- Review test results to see if context guidelines are being followed
Summary not generating:
- Ensure you’ve completed initial site analysis
- Try running a few tests to build the knowledge graph
- Manually refresh the summary after adding new functionality
For more specific guidance on writing effective project context, see our Project Context Best Practices.