The concepts, skills, and habits that turn AI into more than a tool — so you get more done, do better work, and finally have something that thinks alongside you.
Delivered one-on-one to achieve real personalization:
Every session increases your productivity from day one — you leave each one with something that works, not theory for later.
Most people stop at the first two levels — and quietly cap how far they can go. The real leverage is at the top, and the top runs on the things only you bring. Automation → Augmentation → Collaboration
The busywork of moving information around — gathering it, copying it, filing it, connecting one system to another. AI does the manual labor, faster and without slips.
e.g. Auto-file every new invoice and log it to your tracker.
LinearReshaping content that already exists — summarizing, drafting, reformatting, translating. You've already decided what it should say; AI gives it shape.
e.g. Turn a messy call transcript into a clean one-page summary.
LinearA genuine back-and-forth partner. You think with it to reach answers you couldn't reach alone — shaped by your judgment, taste, and experience, the things the model can't know.
e.g. Talk through a hard call with something that knows your business and pushes back.
ExponentialLevels 1 and 2 are real wins — they free your time and teach you the tool. Once they're running, you're free for Level 3 — where your work starts to multiply.
Feed the model what only you know — background, constraints, examples, goals.
Tell genuinely good work from work that just sounds right — and spot what's missing.
Break work into the right pieces: what to hand over whole, what to split.
Refine the output and the prompt — improve the machine, not just the output.
Wire AI into how you actually work: from one-off chat to repeatable process.
Know where the tool's limits are — and whether you've given it enough to do the job well.
AI can match almost anyone's baseline work — but not these. They start to show at Level 2, and become your real edge at Level 3.
Your sense of what's good — the aesthetic and quality bar only you hold.
What you know about your field that the model simply doesn't.
The calls you make on the output: keep, kill, reshape.
Reading meaning and nuance the model takes literally.
Your experience and scars — the situations you've lived that inform the work.
How much risk you'll accept — what must be safe vs. where you can be bold.
The reasoning engine. General, powerful, stateless. A commodity that gets better and cheaper over time.
Your knowledge, files, examples, rules, history. The thing that makes the work yours. The durable asset.
The brain is rented and replaceable. The context is owned and permanent. Build on what you own.
A reasoning engine — general, stateless, swappable. Knows nothing about you until you give it context.
Its working memory for a task. More isn't always better — there's a sweet spot.
Identity, task, context, constraints, output format.
A reusable instruction set that does a specific job the same way every time.
A concrete thing you keep — a doc, dashboard, report, file.
A link to an external system so the brain reads and writes real data.
Makes work run on its own — on a clock or on an event.
Durable knowledge the brain pulls across sessions — in files you own.
A normal prompt gives one answer. An agentic workflow carries out a multi-step process on its own — choosing steps, using tools, and checking its own work.
You ask, a schedule fires, or an event happens.
The objective + the skill that defines how.
Folders (memory) + live systems (connectors).
Run code, search, edit files, call APIs.
Branching and checkpoints to catch errors.
The actual work done on the data.
Where the finished artifact lands.
What persists so the next run is smarter.
Numbered folders are the stages, plain-text files carry the context, and every output is editable before the next stage runs — the folder structure does the orchestration.
The rule that matters most: keep Layer 3 (stable) separate from Layer 4 (per-run).
workspace/ ├── CLAUDE.md ← L0 identity ├── CONTEXT.md ← L1 routing ├── references/ ← L3 factory └── stages/ ├── 01_research/ │ ├── CONTEXT.md ← L2 │ ├── references/ ← L3 │ └── output/ ← L4 ▸ review ├── 02_draft/ … └── 03_final/ …
| Agentic piece | ICM equivalent | What they share |
|---|---|---|
| Trigger | Running the pipeline (drop input into stage 01) | The signal that starts the job |
| Goal + Instructions | Layer 0/1/2 — identity, routing, contract | What role to play, what "done" means |
| Context / Sources | Layer 3 references + Layer 4 inputs | What the agent must know |
| Tools | Local scripts (the non-AI steps) | Work that doesn't need the brain |
| Decisions + QA | The review gate at each output/ | Quality checked before continuing |
| Destination / Artifact | Layer 4 output/ · runs/ | The kept result |
| Memory | Layer 3 factory + runs/ history | What makes the next run smarter |
Same anatomy. An agentic workflow is the pieces of one autonomous run; ICM lays those pieces out as folders so a human can see and steer every step.
Solve Levels 1 & 2 to free your time and learn the tool. Operate at Level 3 to multiply yourself.