Certified RAG, Agents & Automation
What is RAG
Module: RAG & Knowledge
Retrieval-Augmented Generation grounds answers in your own documents instead of model memory.
In practice: A support bot that quotes your help-centre.
Try It Yourself
A support bot that quotes your help-centre.
Lessons
▶️ 1. What is RAG
▶️ 2. Why RAG matters
▶️ 3. Chunking documents
▶️ 4. Embeddings explained
▶️ 5. Vector search
▶️ 6. Prompting with retrieved context
▶️ 7. Citations and trust
▶️ 8. RAG failure modes
▶️ 9. What is an AI agent
▶️ 10. The observe-think-act loop
▶️ 11. Tools and function calling
▶️ 12. Planning and subgoals
▶️ 13. Agent memory
▶️ 14. Guardrails for agents
▶️ 15. Multi-agent systems
▶️ 16. When not to use agents
▶️ 17. AI in workflows
▶️ 18. Triggers and events
▶️ 19. Connecting tools
▶️ 20. Human-in-the-loop
▶️ 21. Batch processing
▶️ 22. Error handling and retries
▶️ 23. Monitoring AI workflows
▶️ 24. Scaling automations
▶️ 25. Getting the most from ChatGPT
▶️ 26. Working with Claude
▶️ 27. Using Google Gemini
▶️ 28. Prompting Grok
▶️ 29. Using DeepSeek
▶️ 30. Perplexity for research
▶️ 31. Microsoft Copilot
▶️ 32. Choosing the right tool
▶️ 33. Matching model to task
▶️ 34. Reasoning vs speed
▶️ 35. Context window needs
▶️ 36. Cost considerations
▶️ 37. Multimodal needs
▶️ 38. Open vs hosted models
▶️ 39. Benchmarks vs reality
▶️ 40. Switching models
Course Home