For AI agents: an index of this guide is available at https://www.plungeai.com/guide/llms.txt. Append .md to any page URL, or send Accept: text/markdown, to get markdown. The developer documentation is at https://www.plungeai.com/docs/llms.txt.

Documentation Index: fetch the complete documentation index at /llms.txt. Use this file to discover all available pages before exploring further.
Feedback

Every delivery waits for your sign-off on Deliverables, or from the review link in your email. Approvers and sponsors decide; a technical lead decides on technical deliveries.

  • Approve accepts the version you see.
  • Request changes sends it back with your note and uses one review round.

A Small includes one review round; a Medium and a Large include two. A round fixes what was agreed. A request past the included rounds becomes a change order.

Go-live

A build ends on Go-live. The deployed URL must answer and the test report must pass before the approver can accept it. If either fails, the page says why and the button stays off.

Before a build starts, our agents write its spec pack: the requirements, an effort estimate (you see a range of days, never our hours), a clickable prototype and a test charter. You approve the charter’s pass mark before any test result is shown. Today a person builds the system with our coding agent; our software factory takes builds over once it agrees with our own review on 20 of them.

What we delivered lists everything handed over: links, workflows, runbooks, documents and keys. Keys are made on your own PlungeAI account and shown by id and prefix only.