THE PROJECTS

14 deliverables.
Every one earns its keep.

Each chapter that ships a project teaches one concrete skill. Three difficulty tiers each — Normal, Medium, Hard — so you can take the work as far as you want. The capstone is the final.

P1 WEEKLY
Week 1 · AI Foundations

First Contact

"What are we, that we build minds — and what is a made intelligence next to a human being?"

A brief history of AI, machine learning vs deep learning, the Transformer breakthrough, why AI changed after 2022, the types of AI (predictive, generative, conversational, multimodal, agentic, physical), and where AI already lives across every profession — AI as a general-purpose technology like electricity→
P2 WEEKLY
Week 2 · LLM Concepts

Three Models, One Prompt

"What is a machine that predicts the next word but does not know what it means — words, and the Word?"

What a large language model is without any math — tokens, context windows, parameters, training, fine-tuning, and inference, all by analogy — so you can reason about what AI can and cannot do→
P3 WEEKLY
Week 3 · Model Landscape

The Model-Selection Matrix

"What does it mean to count the cost — to value a tool rightly instead of always reaching for the most expensive one?"

The frontier labs and their ecosystems (OpenAI, Anthropic, Google, xAI, Meta, Mistral, DeepSeek, Alibaba/Qwen, Microsoft), why every provider ships a family of models (flagship, mini, nano, reasoning, realtime), why smaller models exist, the large-vs-small tradeoffs, and open vs closed weights→
P4 WEEKLY
Week 4 · Prompting

One Email, Three Ways

"What is a word fitly spoken — and why does clarity, being truly understood, carry such weight?"

Prompting reframed as communication, not incantation — clear objectives, context, examples, iterative refinement, role prompting, few-shot, chain-of-thought conceptually, and reusable templates→
P5 WEEKLY
Week 5 · Tool Selection

Deck in an Hour

"What does it mean to test everything and hold fast to what is good?"

Moving from "I use ChatGPT" to "I choose the best tool" — the specialized landscape of general assistants, image, video, audio, music, document, meeting, translation, research, and coding tools, and how to evaluate which one fits a task→
P6 WEEKLY
Week 6 · Writing · Meetings

Inbox & Meeting Makeover

"What does it mean to work heartily, as for the Lord, when the tool makes it easy to be sloppy?"

Using AI for the daily work of words — writing, email, reports, brainstorming, and turning a messy meeting into structured notes and owned action items — while keeping your voice and verifying every commitment→
P7 WEEKLY
Week 7 · Research · Docs

Summarize and Verify

"What did the noble Bereans do that we must do with every AI answer — examine it to see if it is so?"

AI for research, summaries, reading a long document, spreadsheets, and decision support — with the discipline of grounding a summary in its source and catching the fabricated claim→
P8 WEEKLY
Week 8 · Verification

The Fact-Check Gauntlet (MIDTERM)

"What does it mean to test the spirits — to refuse to believe every confident claim?"

Hallucinations, bias, confidence versus correctness, outdated knowledge, fabricated citations, verification strategies, human oversight, and when NOT to use AI — plus the cumulative midterm covering Weeks 1-8→
P9 WEEKLY
Week 9 · Image · Video

Generate on Brief

"What does the commandment against false witness ask of us in an age of synthetic images?"

Generative image tools (Midjourney, DALL·E, Flux) and how image prompting differs, generative video (Veo, Runway, Sora), and the rights, likeness, and provenance questions that come with synthetic media→
P10 WEEKLY
Week 10 · Voice · Audio

Your Voice, With Consent

"The sheep know the shepherd's voice and flee a stranger's — whose voice is it, really, when it is cloned?"

Text-to-speech and voice cloning (ElevenLabs), audio overviews of a document collection (NotebookLM), music generation, and the ethics of consent, disclosure, and misuse when a voice can be copied→
P11 WEEKLY
Week 11 · Local · Cloud

Frontier vs Local Showdown

"What does it mean to guard the good deposit entrusted to you — to treat private data as a trust?"

The tradeoffs between frontier cloud models (largest, smartest, newest, but privacy and subscription costs) and local models you run yourself (Ollama, LM Studio, GPT4All — private, free per use, offline, but limited by hardware), and when privacy forces the decision→
P12 WEEKLY
Week 12 · Prompt Design

Your Prompt Library

"What does it mean that the wise lay up knowledge — that good work should be stored and reused?"

Turning one-off prompts into reusable, templated assets — variables and placeholders, organizing a library by role and task, sharing across a team, versioning, and evaluating prompt quality→
P13 WEEKLY
Week 13 · Agents

Delegate to an Agent

"What does it mean to give an account of your management — when the work was done by an agent?"

What an AI agent is and how it differs from a chatbot — multi-step reasoning, tool use, memory, autonomous workflows, human-in-the-loop, personal and enterprise agents, and digital coworkers — with the accountability that delegation never removes→
P14 FINAL
Week 16 · Future · Capstone

Transform Your Work (FINAL)

"What does it mean to commit your work to the LORD, so that your plans are established?"

Where AI is heading — reasoning models, multimodal and video AI, robotics, scientific, healthcare and education AI, personal AI, AI hardware, wearables, and voice interfaces — the enduring human skills, and a capstone that transforms one real part of your own work with AI→