When tests become intelligent: AI-driven checks with QF-Test

In this special webinar, we’ll show you how to get the most out of the new AI integrations in QF-Test. With QF-Test 10, you can use AI to test non-deterministic UIs, validate UI components based on semantic criteria, generate test data, and much more.

Materials

• Presentation (PDF)
• QF-Test Connected MCP Server (Public Preview)
• AI browser interaction demo (.qft)
• AI data driver demo (.qft)

Contents

Artificial Intelligence

A Large Language Model (LLM) auto-completes text prompts according to previously trained statistical connections.

Our Mission

QF-Test provides AI integrations that increase the productivity of test automation engineers without calling the quality of the results into question.

QF-Test builds on the expertise of QA professionals without replacing them.

AI in QF-Test will always remain optional.

„Bring Your Own Model“

• More flexibility
• No extra costs
• Better data privacy

AI Configuration

Your key to all AI functionality in QF-Test

Check text with AI

Semantic text checks in the UI of the application under test.

Use cases:

• Testing a chat bot integration
• Checking the semantic content of text
• Checking the language of text

ai.ask and the AI Scripting Module

Send LLM requests in any scripting context.

Use cases:

• Test data generation
• Advanced test run integrations

Test generation with QF-Test – Sneak Preview

• Level 1: Test cases and test steps are generated from an existing test definition.
• Level 2: QF-Test agent executes pre-planned test steps; the interactions are recoded. A robust, repeatable test is created.

QF-Test MCP Server

MCP (Model Context Protocol): Integrating external services into an LLM tool

Future versions of QF-Test Pro will include an integrated MCP server. This will enable agent-based workflows with QF-Test.

Advantages over other automation MCPs:

• Controlling Windows, iOS, Android, Java, and web applications
• Strong component recognition by combining QF-Test intelligence and artificial intelligence

The experimental QF-Test Connected MCP Server (Public Preview) allows integrating QF-Test into agentic workflows today.

AI and Test Result Evaluation

• Explain test failures and suggest corrective actions
• Analyze “component not found” errors
• Analyze text comparison diffs
• Summarize test reports

Your ideas are welcome!

What‘s the Price?

• Basic AI features such as AI checks or test suite generation are and will remain included in the standard price of every QF-Test license.
• “Bring your own model”: Costs for using AI itself may arise depending on the chosen model and provider.

In the future:

• Advanced features such as integrating QF-Test into agent-based workflows via MCP will require a QF-Test Pro license.
• If there is sufficient interest: Secure, privacy-compliant access to AI models directly via QF-Test.