Skip to main content
Version: August 2026 - Dify 1.16.1

🧙 Introduction to Testus Patronus

Welcome to the Testus Patronus workshop! This hands-on tutorial is designed for the EuroSTAR Software Testing Conference, where you'll learn how to build your own AI assistant using Retrieval-Augmented Generation (RAG) with a focus on software testing use cases.

✨ By the end of this workshop, you'll have built a magical AI assistant that can help testers understand requirements, generate test cases, and answer technical questions!

Dify Instance Portal
Your AI Assistant Portal

Workshop release baseline: The August 2026 workshop is frozen on Dify 1.16.1 at commit 6f8ed69ee15f9a2e7189ca066275e973d091d1e9. This version preserves the 1.9.1 exercise outcomes while documenting the verified 1.16.1 controls, screenshots, and importable DSLs. There is no floating latest documentation choice.

🎯 What You'll Learn​

📚 Workshop Structure​

The workshop is divided into four main exercises:

1. 🧙 LLM Configuration​

  • Set up your Dify instance
  • Configure Azure-hosted GPT models
  • Create your first chatbot
  • Test basic LLM capabilities

2. 📥 Knowledge Ingestion​

  • Understand chunking strategies
  • Upload Jira issues manually
  • Use the API for structured ingestion
  • Compare different knowledge base approaches

3. 🤖 AI Chatbot Setup​

  • Create a RAG-powered chatflow
  • Connect knowledge retrieval
  • Design effective prompts
  • Prevent hallucinations
  • Publish your chatbot

4. 🎯 Advanced Prompting & Relevance Tuning​

  • Refine prompt templates
  • Tune retrieval parameters
  • Validate with test queries
  • Improve answer quality

🛠️ Prerequisites​

Before starting the workshop, ensure you have:
  • Basic understanding of software testing concepts
  • Familiarity with Jira or similar issue tracking systems
  • Access to the workshop environment (will be provided)
  • A modern web browser (Chrome, Firefox, or Edge recommended)

🚀 Getting Started​

To begin your magical journey:
  1. Review the prerequisites above
  2. Set up your Dify instance (Exercise 1)
  3. Follow the exercises in order
  4. Complete the hands-on tasks in each module

💡 Need Help?​

If you encounter any issues, have questions or would like to organize a session:

Ready to begin? Head to Exercise 1: LLM Configuration to start building your magical AI assistant! 🧙