Explore Prompts

Design an agent that improves error handling: retries, timeouts, and clearer exception types. Require integration tests and telemetry validation post-deploy.

Create a workflow to propose UX copy changes, test via A/B, and ensure no dark patterns. Include an ethics checklist and rollback criteria.

Design a controlled translation system: glossary, style guide, human review, and back-translation checks. Integrate with MCP and require provenance logs.

Design an agent to improve alt-text and form labels, requiring neutral phrasing, avoiding sensitive inference, and validating with accessibility tests.

Create a plan for coding standards that includes auto-fixers (formatters) and a “fix-it PR” bot, with reviewer load controls and staged rollout.

Design a system to generate API docs from code annotations and schemas, but require verification via integration tests and manual spot checks.

Design a loop to improve job scheduling: fairness, retries, visibility timeouts, and backpressure. Require load testing and chaos testing in staging.

Create an agent that validates docs examples by executing them in a sandbox, checks links, and ensures version correctness. Propose fixes with evidence.

Design a plan to self-improve ranking/retrieval safely: offline eval sets, interleaving/AB tests, bias checks, and rollback on metric drops.

Create an agent to tune caches: TTLs, invalidation, and hit rates. Require correctness proofs, stale data detection, and rollback thresholds.

Design an agent that improves ETL reliability: retries, idempotency, checkpoints, and backfills. Require correctness validation and cost constraints.

Create a strict policy for edits to auth code: mandatory human review, extra tests, formal checks, and staged rollout. Include “never auto-merge auth changes.”