Does good AI work come from better prompting or from better systems?
A prompt works once, for one agent. A system of clear tasks, reusable skills and a fixed sequence of checks works again with every draft, before a human decides. Such a system rests on six parts: clear tasks instead of vague instructions, skills an agent can reuse, a self-check before every submission, review gates that go through the draft once more, a human decision at the end, and a feedback loop that carries every correction back into the system. Content that leaves the building follows a fixed sequence of eleven gates, from Business Context to Feedback Memory. Brand Voice and Claims & Proof check midway, directly followed by Risk & Legal Preflight. Human approval stands at the end, before every publication.
How a draft reaches approval
Content that leaves the building follows a fixed sequence of eleven gates, from Business Context to Feedback Memory. Brand Voice and Claims & Proof check midway, directly followed by Risk & Legal Preflight. Human approval stands at the end, before every publication.
Each single gate returns one of four answers. Pass, when the draft can continue. Revise, when it needs a change. Block, when it cannot continue. Escalate, when a human or a specialist has to decide.
Where the final decision stays
Human Approval stands before every publication. No gate before it replaces that. Every run ends at Feedback Memory, the feedback that goes back into the system and shapes the next draft.
From the YMAD standard
YMAD Quality Gates and Skills, internal ZukunftBilden standard document, status 30 April 2026.
- Eleven gates in a fixed sequence for external outputs, from Business Context to Feedback Memory
- Each gate decides between pass, revise, block and escalate
- Brand Voice and Claims & Proof run before Risk & Legal Preflight
- Review Submission and Human Approval stand before Publish Handoff
This note keeps growing
2026-09-02: Planted from the YMAD standard document on gates and skills.