Courses
Pick your track
Each course has its own modules, quizzes, badges, and certificate. Progress in one does not shortcut the other — but they are designed to build on each other.
A ground-up Python course, beginner to staff-level. Modern tooling with uv and ruff, fundamentals, OOP, decorators and typing, the standard library, asyncio, data (NumPy/pandas/polars), testing and quality, performance and parallelism, FastAPI and streaming APIs, packaging and Docker. Ends with an interview workbook that mirrors real senior-engineer loops.
- Modules
- 12
- Lessons
- 50
- Reading
- ~7h
- Projects
- 5
0 / 11 badges
Certificate locked
A ground-up course on building AI agents that ship: LLM APIs and prompting, RAG with hybrid search, single- and multi-agent orchestration in LangGraph, MCP servers and A2A, evaluation, guardrails, fine-tuning, serving, and deployment. Ends with a specialisation track and a capstone.
- Modules
- 7
- Lessons
- 33
- Reading
- ~4h
- Projects
- 5
0 / 7 badges
Certificate locked
A standards-anchored, deeply technical course on securing AI agents: agent identity models, OAuth flows built for agents, the MCP authorization spec, scoped tool access, secrets brokering, audit and provenance, attacks and defences, governance, and the Microsoft Entra Agent ID platform.
- Modules
- 11
- Lessons
- 25
- Reading
- ~4h
- Projects
- 6
0 / 12 badges
Certificate locked
A research-engineer course on what is inside an LLM: the math and PyTorch foundations, neural nets and sequence models, the Transformer and building GPT from scratch, pretraining objectives and scaling laws, post-training (SFT, RLHF, DPO, reasoning RL), inference and serving (KV cache, quantization, speculative decoding), frontiers (MoE, Mamba, multimodal, agentic models), and evaluation and interpretability. Ends with a portfolio of buildable projects and an interview workbook.
- Modules
- 9
- Lessons
- 35
- Reading
- ~5h
- Projects
- 5
0 / 9 badges
Certificate locked