The Expedition
11 milestones, sequenced from fundamentals to production systems. Follow the rail or jump to any station.
Understand what an AI engineer ships, then run real inference on pre-trained models — and reason about their token and cost behavior
Make model output reliable — prompts, tool/function calling, and schema-valid JSON
Ground answers in your own data — embeddings and retrieval with a vector database and a metadata store
Build agents that reason and act — tool-use loops, multi-agent coordination, and orchestration
Give agents durable recall — semantic, episodic and procedural memory, context-window engineering, and long-term memory stores that survive across sessions
Build production agent graphs with LangChain and LangGraph — LCEL chains, stateful graphs, D1-checkpointed memory, human-in-the-loop, and tracing
Prove it works and ships safely — evals, red-teaming, guardrails, and gateway-level observability
Take it to production — deploy, scale, cost-control, and CI/CD
Optional track — customize models with LoRA, RLHF and dataset curation when prompting is not enough
Optional track — GCP, Docker and Kubernetes for portability and comparison off the primary path
Optional track — software-engineering foundations (SOLID, ACID, SQL, CI/CD) plus LlamaIndex and communication