§ 001 / THE LAB COURSE
The Local AI Engineering Lab
Eight build-first modules. Every open model runs on hardware you control, and every module ends in a benchmark you publish.
Connecting sign-in... If this never resolves, sign-in is misconfigured or blocked. Email pat@bmdpat.com and mention the course.
§ 002 / CURRICULUM
- 01FOUNDATIONS90m
LLM Playground on Local Hardware
Train a tiny GPT, then sample it every way
Proof: A decoding-strategy benchmark table, quality vs tokens/sec on your card.
- ADAPTATION105m
Fine-Tune Llama 3.1 8B into a Support Bot
LoRA on one consumer GPU, measured before and after
Proof: A before/after eval table plus the VRAM and wall-clock cost of the tune.
Finish module 01 to unlock
- RETRIEVAL100m
Build a Local RAG Pipeline
Chunk, embed, retrieve, and guard, all on your box
Proof: A retrieval-quality table comparing three chunking strategies.
Finish module 02 to unlock
- AGENTS110m
Build an Ask-the-Web Agent
Routing, reflection, and tools over MCP, priced against the API
Proof: A local-vs-API cost curve for the same agent trace.
Finish module 03 to unlock
- REASONING105m
Add a Deep Research Capability
Spend inference-time compute on a local reasoning model, and measure it
Proof: An inference-time-scaling curve, answer quality vs thinking tokens.
Finish module 04 to unlock
- GENERATION95m
Ship a Local Diffusion Image Service
Text-to-image behind a small API, benchmarked across quant levels
Proof: A VRAM/latency/quality grid across quant levels for the same prompt.
Finish module 05 to unlock
- OBSERVABILITY115m
Harden the Agent - Memory, Guards, and Observability
Make Module 4's agent safe to leave running
Proof: A red-team log, injection attacks attempted vs which guard caught them.
Finish module 06 to unlock
- CAPSTONE120m
Capstone - Ship One Production-Shaped Local Agent
Compose the seven parts into one system a stranger can run
Proof: A public repo plus a lab report with at least one real benchmark table.
Finish module 07 to unlock