Your build starts here
Replace bracketed details with your own goal, context, and checks. Keep the first build small enough to inspect.
Design [AI feature] around [user journey]. Define its required evidence, model inputs, output shape, and allowed tool actions. Keep retrieved content separate from task instructions, and enforce schema validation and permissions in trusted application code. Specify loading, streaming, cancellation, missing-evidence, malformed-output, timeout, and denied-access behavior. Create representative normal and failure examples with expected outcomes. Implement the smallest complete flow using existing conventions, then report which checks establish product behavior and which dependencies still need configuration.Make this prompt yours
Replace bracketed fields with your goal, current behavior, and relevant evidence. Keep requirements that affect the task. Check the result against the acceptance criteria you supplied.
The docs behind it
These references explain the underlying concepts and APIs. The prompt templates and project plans are original examples to adapt to your own setup.
- JSON Schema — Object properties and required fields
- AWS Builders' Library — Timeouts, retries, and backoff
- MDN — Streaming server-sent events
Documentation links checked .
Editorial review · October 28, 2026
Limited: Original instructional template; not executed. Failure-behavior prompt requests a bounded product contract and representative fixtures, not proof that a deployed AI system is safe.