Explore Prompts

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.

Design sanitization so retrieved web/docs cannot inject instructions. Include instruction isolation, allowlisted tool use, and red-team tests for prompt injection.

Create a research agent that uses search APIs and page fetchers to gather evidence for a proposed code change. Require citations and source quality scoring.

Design a reproducible build pipeline: pinned deps, lockfiles, hermetic builds, SBOM generation, and provenance attestation for every self-edit.

Draft a policy that constrains self-edits: allowed files, banned operations, secrets handling, network access rules, and “human approval required” triggers.

Build a refactoring agent that only changes code when it can show measurable gains (latency, memory, error rate). Include baseline capture and regression detection.

Create a multi-agent design: Editor drafts patch, Reviewer critiques, Verifier runs checks, Operator manages deploy. Define handoffs and stop rules to prevent loops.