Learn AI for testing through 20 hands-on projects
This course starts with local AI tools and prompt engineering, moves into apps and automation, then expands into LangFlow, RAG, MCP, CrewAI agents, and custom MCP server creation. Use this page as your student guide through the complete learning journey.
What you will build
Test generators, prompt frameworks, full-stack QA apps, LangFlow pipelines, RAG systems, MCP workflows, CrewAI agents, and custom MCP servers.
What you will practice
Prompt design, browser automation, API framework work, no-code orchestration, retrieval design, multi-agent crews, and tool-connected AI execution.
How you will learn
Each project gives you a clear outcome, the main concepts to focus on, and direct links to the repo assets used in the session.
How the course is grouped
The projects are grouped so you can progress from fundamentals to advanced integrations in a logical order, instead of seeing AI testing as a random collection of tools.
Phase 1: Local AI and Prompting
Projects 1 to 4 establish private local LLM workflows, prompt frameworks, and reusable prompt assets.
Phase 2: Apps, Agents, and Automation
Projects 5 to 10 move into product-like UI, JIRA agents, no-code automation, and AI-assisted workflows.
Phase 3: LangFlow and Retrieval Systems
Projects 11 to 15 cover LangFlow basics, RAG theory, visual flow engineering, modular RAG apps, and embeddings.
Phase 4: MCP, CrewAI and Custom Agents
Projects 16 to 19 extend the course into MCP workflows, Python for AI, CrewAI multi-agent systems, and building custom MCP servers.
How you move through the program
Think of this as the learning route for the full blueprint. Every later phase becomes easier once the earlier phase is clear.
1. Start with control
Projects 1 to 4 show how to control prompt behavior, model behavior, and input structure before introducing more moving parts.
2. Move to useful systems
Projects 5 to 10 turn AI into visible workflow value: apps, agents, JIRA integration, and content or bug workflows.
3. Learn retrieval and flow engineering
Projects 11 to 15 close the loop by moving from LangFlow fundamentals to retrieval theory, flow engineering, product code, and embeddings.
4. Extend into MCP and multi-agent systems
Projects 16 to 19 connect AI to MCP orchestration, Python foundations, CrewAI multi-agent crews, and building custom MCP servers from scratch.