Explore Prompts

Create a plan quality rubric: completeness, dependency ordering, risk controls, verification steps, and rollback. Provide examples of high-quality vs low-quality plans.

Design a questioning strategy: when to ask, how to propose defaults, and how to avoid excessive back-and-forth. Include a “progress-first” interaction model.

Create policy profiles for user tiers: consumer, enterprise, regulated. Include stricter tool permissions, logging requirements, and human approval gates by tier.

Design an enterprise multi-tenant architecture: per-tenant tool scopes, data isolation, policy profiles, and audit reporting. Include threat model and testing plan.

Design secrets handling: vault integration, short-lived tokens, environment isolation, and audit trails. Include tests to ensure secrets never appear in outputs or logs.

Design a privacy-by-design approach: data minimization, redaction, retention limits, and access controls for agent logs and memory. Include a compliance-friendly checklist.

Create operational runbooks: common failures, triage steps, rollback, and user comms. Include SLO breaches, tool outages, and prompt regressions.

Write a safety case template: intended use, hazards, mitigations, tests, monitoring, and rollback. Include what evidence is required to ship the capability.

Create a policy for explanations: cite sources, show assumptions, and label uncertainty. Provide UI patterns for “why this tool was called” and “why this conclusion.”

Design an artifact-centric workflow: agents produce plans, checklists, diffs, and reports as first-class outputs. Include templates and how artifacts enable auditing and reuse.

Design caching layers: retrieval cache, tool result cache, and response cache. Include invalidation rules, privacy constraints, and how to measure cache hit value.

Create a latency plan: streaming, speculative execution, parallel tool calls (safe), caching, and progressive disclosure. Include how to avoid race-condition errors and maintain correctness.