← Donecraft, the book

Donecraft for AI

AI can move a project fast.
Donecraft makes it accountable.

AI agents are fast. The work they produce still has to be understood, verified, and something a human can stand behind — whether that’s code, a plan, or any other deliverable.

Donecraft breaks any AI-run project into small outcome loops and requires evidence before generated work becomes an accepted result.

See how it works See it applied to coding

AI may produce attempts.

Donecraft controls when those attempts become accepted outcomes.

How it works

01

Define the result

Describe what must exist when the work is genuinely finished — not merely which code the agent should write.

02

Bound the attempt

Give each agent one outcome, a controlled code surface, explicit inputs and limited authority.

03

Verify independently

Implementation, testing, security and integration should not all depend on the same agent’s interpretation.

04

Accept or revise

Generated code remains an attempt until the evidence shows that the intended result actually exists.

Output → Process → Input → Revision

This loop is implemented in OPIR, Donecraft’s open-source project runtime — the software that bounds, verifies and tracks AI-generated work.

View OPIR on Codeberg →

Six ways AI coding breaks down

Software development is where these failure modes are best documented and most costly — the same pattern shows up in any AI-run project. Each one has a Donecraft response. Explore the full library or jump straight to a category.

Faster generation is not the same as a better outcome

The relevant question is not — “How much did the AI produce?”

It is — “How much verified, understood and accountable capability did the project create?”

Explore the complete AI coding problem map →