Orientation Primer Frontier vs. Local Metal Calibration Warm-Up
Module 0: Primer, Practical Use Cases & Dispelling Common Myths
The practical tinkerer’s stance: approach LLMs as untrusted, non-deterministic engines. Grounded in our everyday vehicle metaphor, this primer examines why generative art became a cultural battleground, tracks capability velocity from early video artifacts, breaks down four tactical IT use cases, dispels persistent industry myths (RLHF agreeableness and cloud subpoena realities), and compares frontier cloud vs. local metal inference. Includes hands-on calibration exercises.
The Crate Motor Tokens & KV-Cache Math Hands-On Lab
Module 1: Foundational GenAI for the Tinkerer
Strip away the vendor hype: understand probabilistic token prediction, context bloat, clean-room datasets, and how to treat LLMs as untrusted black-box appliances.
Clean Fuel & Cruise Control NotebookLM & YAML Gems Hands-On Lab
Module 2: Grounded GenAI Usage: NotebookLM & Gems
Moving from unconstrained open-web interaction to more targeted interactions and outcomes. Build structured YAML system instructions with Gemini Gem Building and see how RAG and GenAI can truly help to expedite data processing and learning.
Agentic Chassis MCP & Planning Loops Hands-On Lab
Module 3: Agentic IDEs & AI Pair Programming (Coming Soon)
Moving from reactive autocomplete and lots of copy/pasting to autonomous agent loops in modern IDEs. Build custom deterministic skills, execute planning workflows, and learn how to free up time to do more important things like learning more, or even taking a break.
The Engine Swap GGUF Quantization & VRAM Hands-On Lab
Module 4: Local Open-Weight Inference & Hardware Architecture (Coming Soon)
Taking full control of your inference stack. Profile VRAM math, navigate GGUF quantization, and spin up private OpenAI-compatible REST server endpoints with LM Studio or Ollama.
Drivetrain & Brakes Ollama & Tool Runners Hands-On Lab
Module 5: Custom Autonomous Agent Harnesses & Tool Runners (Coming Soon)
Building harnesses with Ollama and PowerShell/Python tool runners. Maximize the capabilities of an on-device model via targeted skills and constraints that you can have near full control over.
Persistent Flight Recorder SQLite WAL & Hybrid RRF Hands-On Lab
Module 6: Enterprise Cognitive Memory & Hybrid RAG Architecture (Coming Soon)
Constructing persistent memory engines and your own personal GenAI solution to continue driving the benefits of GenAI offline.
Bull-Bar & Armor Prompt Guard & Triage Hands-On Lab
Module 7: AI-Augmented Workflows & Automation (Coming Soon)
Explore ways to turn everything you have created thus far into an agentic agent that can help lighten every day tasks and maybe one day, when you need it, help you with much more critical tasks.
State Inspection Enterprise Production Capstone Project
Module 8: Capstone: Enterprise AI Agent & Course Wrap-Up (Coming Soon)
The final proving ground: Bring it all together and explore documenting it, writing up your own journey, and developing a plan to either integrate in your personal life or make a pitch at work.