Build with P2HS AI - P2HS Documentation

P2HS AI turns a project request into a tracked codegen run. The run can estimate cost, collect required user inputs, execute generation, validate the result, and produce a revision for review.

Write an effective request

Describe the outcome, the important user roles, the data the application needs, and any integrations. For example:

Build a customer portal with sign-in, customer profiles,
subscription status, a support request form, and an admin view.
Use the project’s admitted authentication, forms, and record capabilities.

Avoid asking for credentials or embedding provider secrets in prompts or generated client code.

Run lifecycle

Estimate the run when an estimate is available.
Create the run with the project context and requested change.
Supply required user inputs or capability approvals.
Execute and monitor status and timeline events.
Review changes and the resulting revision.
Preview and deploy after validation.

See Codegen lifecycle for the public abstraction and AI credits for the API boundary.