CCraft

Public preview

Try Craft on one real piece of work.

The Lab is the guided practice. Craft is the method and workbench inside it.

Leave with a named task, a CLEAR brief you can paste into ChatGPT, Claude or Copilot, and a No Spoon redesign note — redesign the inherited workflow from first principles. The full path, templates and evidence stay inside membership.

Clickable sampler

Inside Craft

Locked does not mean blank. Each stage shows the change in capability, your role, an artefact, and what joining opens.

Open now

Assist

Change in capability
AI helps you think, draft, or challenge. You still decide.
Your role
At the helm
Example artefact
A named real task and one CLEAR brief you can paste into chat.

Open the first micro-lesson. Leave with a job for chat.

After joining: The full Assist path, working files, and a human-reviewed licence.

Open this lesson →

Inside Craft

After joining

Augment

Change in capability
AI carries several steps across files. You guide and approve.
Your role
In the loop
Example artefact
A repeatable runbook for one recurring job.
Craft diagram of how much help AI carries — chat, working across files, and later file work — with vendor tools as examples.
Chat is conversational. Cowork is working — several steps, you review.

After joining: The Augment lessons, working templates, and progress on your real files.

Excerpt

No Spoon

Change in capability
Redesign the inherited workflow from first principles. Stop automating the old form first.
Your role
Choose deliberately
Example artefact
One No Spoon question plus a first redesign move on a workflow you already run.

Leave with a usable redesign note. The full six-move canvas stays inside Craft.

After joining: The full No-Spoon canvas, Must Keep language, and a standing tool you can re-run.

Open this lesson →

Inside Craft

After joining

Adapt

Change in capability
A proven workflow can run more independently inside rules you set.
Your role
On call
Example artefact
A bounded real-work run with a plan you approved.
Craft diagram showing later file work under Adapt, with you still on call.
Work on files in the terminal later. You remain on call — Plan, Review, Approve.

After joining: Workbench setup, terminal fluency, and the Super Licence path when the work earns it.

Inside Craft

After joining

Safety and memory foundation

Change in capability
Protect the work, preserve its history, and recover if a change goes wrong.
Your role
Human review of captures, experiments, and proposals
Example artefact
A capture: what changed, what was kept, how to recover.

Example capture: “Board pack v3 — kept the risk paragraph; experiment in a copy; recover from Friday’s file.”

After joining: The safety and memory foundation under Assist, Augment, No Spoon, and Adapt — not a separate product tour.

After the sampler

Continue inside Craft

Joining opens the full Assist → Augment → No Spoon → Adapt path, working templates, progress and evidence, a human-reviewed licence, and cohort or Lab context where it is included.

Deeper map

A map you will keep using

How the pieces fit

The model is not the whole system. These layers answer different questions. They are not interchangeable.

  1. Model

    What intelligence is doing the thinking?

    Claude · GPT · Gemini · Grok

  2. Harness

    How is that intelligence equipped to work?

    Chat · Cowork · Code

  3. Connections

    What can the harness reach?

    Connectors · apps · Graph · MCP

  4. Skills

    What reusable method can it perform?

    Research synthesis · decision memo · stakeholder brief

  5. Product

    Which implementation am I opening?

    ChatGPT · Claude Cowork · Claude Code · Codex · Copilot

  6. Agency

    How much of the work does AI carry?

    Assist · Augment · Adapt

  7. My role

    Where do I remain responsible?

    At the helm · in the loop · on call

The model is the intelligence. The harness determines how it can work. Connections determine what it can reach. Skills give it a reusable method.

Agency determines how much responsibility it carries. You remain responsible for the result.

  • Chat harness

    helps me think; I act.

  • Cowork harness

    works through several steps; I review.

  • Code harness

    works directly on files inside rules; I remain on call.

Foundation beneath the stack

Timeline

What protects the work, preserves its history and lets us recover?

Sacred Timeline · captures · experiments · proposals · human review

Before AI changes important work, protect the timeline.