Brief Checker
Would an agent have to guess?
Paste a ticket and the readiness score says what a coding agent won’t find in it. It runs in your browser, by the same rules as the app. The AI rewrite shows the brief it could be, with the questions it would ask you.
Scoring runs in your browser. The rewrite sends the text to our server and to OpenAI to write it; we do not store it.
Paste something to score it.
- +25
Intent
What this achieves and why, in a sentence or more.
- +30
Acceptance checks
Listed under a heading such as “Acceptance checks”, each one a result someone can observe.
- +25
No open questions
Every “Open questions” bullet is answered or struck.
- +20
Context
Files, repositories, links: where the work happens.
The score checks the shape of the ticket, not whether it is right: it cannot tell if your checks are the right ones. That is what the rewrite and your team are for.
The rules are in the open Brief Standard.
Questions
Is my ticket stored?
No. The score runs entirely in your browser. For the rewrite, the text goes to our server and to OpenAI to write it; we don’t store it or use it for anything else.
Why doesn’t my good story score 100?
The score checks four things an agent needs: an intent, acceptance checks under a heading, no open questions, and context such as a file or a link. When one is missing, the list says which. A line like “Acceptance criteria:” without a Markdown heading doesn’t count.
How many rewrites can I ask for?
A few an hour, so there is enough for everyone. In a free workspace the AI writes briefs on every ticket, 50 a month on the built-in AI, and with your own OpenAI key there is no limit.
Can my agent do this too?
Yes. In NEWWORK Projects the MCP tool pm-brief-check scores a draft by the same rules before it is saved.
Give your next agent a brief.
Free for up to 10 people, with MCP for every agent. No credit card.