Knowledge

QA.tech’s knowledge system helps AI assistants understand your project by providing context through knowledge items, global configuration, and auto-generated summaries. This enables more accurate test generation and better project-specific guidance.

​

Types of Knowledge

​

Knowledge Items

Add documentation, links, and text content that AI assistants can reference when generating tests and answering questions. Knowledge items are stored at the project level and shared across all team members. What You Can Add:

• URLs: Link to documentation sites, help pages, API docs
• Text Content: Add custom instructions, project notes, or guidelines

​

Global Context

Global context is included in the AI agent’s prompt for all test executions in your project. Use this to specify project-specific behaviors, requirements, or guidelines that should always apply. What to Include:

• 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

​

Project Summary

An AI-generated summary of your website’s functionality and structure, created by analyzing your pages and user interactions. This summary updates automatically as your site evolves. What’s Included:

• Overview of your platform’s purpose and main functionality
• Key features and user flows
• Important pages and their purposes
• Integration points and external services

To Refresh the Summary:

​

How Knowledge Works

Knowledge has different roles during test creation versus test execution: During Test Creation (Chat & Test Generation):

• AI searches knowledge items for relevant documentation and specifications
• Global context helps the AI understand your product domain
• Project summary provides overall context about your application
• Chat assistants use knowledge to answer questions and suggest tests

During Test Execution:

• Only the generated test steps and global context are used
• Knowledge items are disconnected from the running test
• Tests execute based on the instructions that were created, not the original documentation

This separation means you can safely update knowledge without affecting tests that are already running or scheduled.

​

Project Knowledge vs. Chat-Local Files

Understanding the scope of your knowledge helps you organize it effectively: Project Knowledge (Settings → Knowledge):

• Shared across all chats in the project
• Accessible to all team members
• Permanent and searchable by semantic search
• Best for: Official documentation, stable specifications, product rules

Chat-Local Files (uploaded directly to a chat):

• Only exists in that specific chat conversation
• Other users’ chats cannot access it
• Not added to project knowledge automatically
• Best for: Experimental specs, temporary references, exploratory work

This isolation prevents temporary or incorrect information from affecting other team members’ work.

​

Semantic Search

Knowledge items are automatically indexed using embeddings, allowing the AI to find relevant information based on meaning rather than exact keywords. When you ask a question or generate tests, the system:

1. Analyzes your request to understand intent
2. Searches knowledge items for semantically similar content
3. Provides the most relevant information to the AI assistant
4. Uses clear file names to improve search accuracy

​

Managing Your Knowledge - where to Upload What

Choose the right location based on how stable and official your information is: Upload to Project Knowledge when:

• The information is official, approved documentation
• It describes stable features and requirements
• It contains compliance guidelines or business rules
• It won’t change frequently
• All team members should reference it

Upload to Chat when:

• The information is experimental or exploratory
• It describes new features still in development
• It’s a pull request description or feature branch documentation
• It may be updated or replaced soon
• You’re testing ideas before committing them

​

Adding Knowledge Items

​

Organization Tips

• Use Clear Titles: Make knowledge items easy to find with specific, descriptive names
• Keep Content Current: Regularly review and update documentation links
• Remove Outdated Info: Delete or update knowledge that no longer reflects your product
• Test Your Knowledge: Ask the chat assistant questions to verify it finds the right information
• Avoid Contradictions: When updating specs, remove old versions to prevent confusion

​

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
• Use clear, descriptive titles for better semantic search results

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

Chat-uploaded files not visible to team:

• Remember: files uploaded in chat are conversation-specific
• To share with team, add the file to Project Knowledge instead
• Other team members need to upload it to their own chats, or use project knowledge