Explore Prompts

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.

Define MCP tools for repo read, lint, unit tests, dependency scan, and PR creation. Specify schemas, permissions, error codes, and deny-by-default access.

Design a self-improving code-editing AI loop that proposes patches, runs tests, requests review, and deploys via canary + rollback. Include explicit safety gates and audit logs.

Create a 90-day plan to build and test 10 product ideas using AGI: selection rubric, MVP pipeline, pricing tests, and kill/scale rules. Include a weekly cadence.

Write an investor memo template for abundance-era businesses: why now, wedge, defensibility, unit economics, and governance. Include a section on ethics and risk controls.

Create a 7-day go-to-market launch plan for an AI-native product: ICP, positioning, demos, distribution channels, and measurement. Include guardrails against hype marketing.

Design an open innovation platform: problem postings, solution generation, evaluation, and funding. Include anti-spam protections and fair contributor incentives.