Building LLM Applications
The planned outline of 15 modules. Lessons are written, run and reviewed before they are published.
Before this track
Planned outline
- Module 1
Start here: LLM features and a zero-cost workbench
Coming soon - Module 2
Model APIs in practice: tokens, state, errors and portability
Coming soon - Module 3
Prompts as code
Coming soon - Module 4
Structured output: JSON, schemas and grammars
Coming soon - Module 5
Streaming, chat interfaces and multimodal input
Coming soon - Module 6
Tool calling
Coming soon - Module 7
Embeddings and vector search
Coming soon - Module 8
Retrieval-augmented generation in code
Coming soon - Module 9
Evaluating LLM features
Coming soon - Module 10
Agents and workflows
Coming soon - Module 11
Model Context Protocol (MCP)
Coming soon - Module 12
Security, safety and privacy
Coming soon - Module 13
Production engineering: caching, cost, tracing, testing and release
Coming soon - Module 14
On-device and in-browser models
Coming soon - Module 15
Adapting models with fine-tuning
Coming soon
Related tools
Official documentation
- modelcontextprotocol.io (modelcontextprotocol.io)
- huggingface.co/docs/transformers.js/index (huggingface.co)
- github.com/pgvector/pgvector (github.com)
- genai.owasp.org/resource/owasp-genai-llm-top-10-2026 (genai.owasp.org)
More in AI and machine learning
- Machine Learning (scikit-learn) (coming soon)
- AI Literacy & Prompting (coming soon)
- Artificial Intelligence (classical AI and soft computing) (coming soon)
- Mathematics for Machine Learning (coming soon)
- All AI & ML tracks
- How we make lessons