Explore Prompts

Design secret-handling: vault integration, redaction in logs, and automated leak scans on diffs, logs, and artifacts. Include fail-closed behavior.

Create a safety case template per capability: hazards, mitigations, tests, monitoring, rollback, and residual risk. Require evidence links and sign-off rules.

Design a reviewer UX: diff summaries, risk flags, test results, and “approve with conditions.” Include prompts that help humans spot hidden risks quickly.

Define autonomy tiers for the self-improver. Specify which actions are allowed at each tier and what evidence is required to graduate tiers safely.

Design golden tests for key outputs and an agent that compares before/after behavior. Include tolerance rules and how to prevent “golden drift” over time.

Create a tracing and logging spec for the self-edit loop: prompts, tool calls, diffs, test results, deploy events, and user impact metrics.

Design a progressive delivery system: canary cohorts, SLO monitoring, automatic rollback, and incident annotations. Include safe defaults and stop conditions.

Define an RFC template the agent must fill: motivation, risks, alternatives, test plan, rollout plan, and monitoring. Require linking evidence and metrics.

Create a permissions matrix for MCP tools: read-only by default, write tools gated, deploy tools require human approval. Include environment separation (dev/stage/prod).

Build a dependency update agent that monitors CVEs, proposes safe upgrades, runs integration tests, and creates changelog notes. Include rollback and pin rules.

Design a gate that blocks merges unless linting, type checks, and security linters pass. Include a policy for exceptions and mandatory justification logging.

Create an agent that writes tests before code changes, targets uncovered branches, and proves coverage deltas. Include mutation testing as a safety check.