Learn to build, deploy and engineer production AI systems.
Hands-on tutorials, interactive labs and production-grade projects across AI Engineering, Generative AI, Agentic AI and Forward Deployed Engineering.
Click another node to explore →
01 — Choose Your Path
Four tracks, one destination
Structured learning journeys from software developer to AI Engineer to FDE.
From software developer to AI Engineer
Master generative AI systems
Build autonomous AI systems
Forward Deployed Engineering
02 — Featured Series
Premium tutorial series
Series-first learning. Multiple chapters, labs and a capstone per series.
Understand LLMs from the inside out: tokenisation, context windows, prompting, structured outputs, function calling, streaming and multimodal inputs. The foundation for everything generative.
End-to-end production RAG: document ingestion, chunking, embeddings, vector search, retrieval, reranking, evaluation and production architecture. From naive chatbot to reliable knowledge system.
Build real agents: tool calling, the ReAct loop, agent memory, planning, error recovery and production agent patterns. Move from single-shot completions to autonomous systems that act.
Move beyond single agents. Build graph-based workflows, multi-agent systems, planning pipelines, human-in-the-loop checkpoints, and integrate tools via MCP.
03 — Interactive Labs
Learn by building
Hands-on labs with starter code, hints and validation steps.
Implement a POST /api/echo endpoint that validates input, returns structured output, and handles errors with proper status codes.
Implement call_structured() that returns a validated Pydantic model from an LLM, with retry on validation failure.
Implement three chunking strategies and measure their impact on a sample retrieval eval.
Implement a VectorStore with embed, insert, and search(filter) methods.
04 — Build Something
Portfolio-grade projects
From beginner chatbots to FDE capstones — build, deploy and demonstrate.
Create an AI chatbot that can hold a coherent conversation, maintain history, stream responses, and refuse harmful requests.
Summarise 50-page documents within token limits while preserving key points, entities and structure.
Answer questions over a private document set with citations, confidence scores, and graceful 'I don't know' behaviour.
The query is embedded and used to search a vector database for relevant chunks. Candidates are reranked by a cross-encoder, the top results become the LLM context, and the model generates a grounded answer with citations.
Your RAG system over internal docs has excellent retrieval scores (recall@5 = 0.91) but users complain the answers are wrong, vague or cite the wrong source. Diagnose the problem.
A tier-1 bank wants an AI assistant over internal policies, procedures and customer-support documentation. Support agents should get instant, cited answers to policy questions. Compliance must be able to audit every query and answer. Data access must respect role-based permissions.
05 — Latest Chapters
Fresh from the curriculum
Recently published chapters across series.
Every learning experience moves you from concept to portfolio.
Not a blog. Not a course. A connected engineering curriculum that takes you from software developer to production AI Engineer to Forward Deployed Engineer.
Learn
Understand the concept
Build
Guided implementation
Experiment
Modify and observe
Ship
Production patterns
Demonstrate
Portfolio project