Course · Interview foundations
AI Agents for Data Engineers
Free AI agents course: how agents work, the agent loop, workflows vs agents, tools and MCP, evaluation and safety, explained simply with runnable Python code.
- Lessons
- 7
- Interview questions
- 0
- Projects & case studies
- 0
- Reading time
- ~1 h
Your progress
Saved in this browser onlyCourse structure
- 1 lessonStart hereThe complete overview of the course in one read.
- 3 lessonsIntermediatePatterns used in production pipelines.
- 3 lessonsAdvancedPerformance, internals and edge cases.
Practise
Lessons
Work through the lessons in order. Completed lessons show a tick; lessons you have opened are outlined.
Start here
The complete overview of the course in one read.
Intermediate
Patterns used in production pipelines.
- Workflows vs AI Agents: When to Use EachWhen to build a fixed LLM workflow and when you need an AI agent: predictability, cost, testing and flexibility compared, with a runnable Python workflow.
- MCP (Model Context Protocol) Explained Simply, with CodeWhat the Model Context Protocol (MCP) is, how MCP servers and clients talk, what tools, resources and prompts are, and how to use it safely, with runnable code.
- Agent Memory and Planning: How AI Agents Remember and PlanHow AI agents remember and plan: short-term and long-term memory, plan-then-execute, and re-planning when a step fails, with runnable Python examples.
Advanced
Performance, internals and edge cases.
- Evaluating and Securing AI AgentsHow to evaluate AI agents with repeated task runs and success rates, and how to secure them against wrong actions and prompt injection, with runnable Python.
- Multi-Agent Systems: When and How to Use Several AgentsWhat multi-agent systems are, the coordinator and specialist pattern, when several agents beat one, and the costs they add, with a runnable Python example.
- Build an AI Agent Project: A Support Agent with Tools, Limits and EvaluationBuild a complete AI support agent in Python: checked tools, the agent loop, step limits, logging and an evaluation on realistic tasks, ready for a portfolio.
Resources
Related courses
- LLMsFree LLM course for AI engineers: how large language models work, tokens, embeddings, attention, generation and prompting, explained simply with runnable code.
- RAGFree RAG course for AI engineers: how retrieval-augmented generation works, chunking, embeddings, hybrid search, reranking and evaluation, with runnable code.
- PythonFree Python course for Data Engineering: generators, CSV and JSON files, APIs, pandas, error handling and pytest, with runnable code and interview questions.
