Explore Prompts

Define specialist agent roles with distinct prompts, tools, and constraints. Provide handoff rules and an evaluation plan to ensure specialists outperform a monolith.

Design a disagreement resolution policy: majority vote, weighted expertise, verifier override, or human arbitration. Include criteria for which method applies and how to log rationale.

Design a typed A2A message schema: intents, constraints, artifacts, and status updates. Include versioning strategy and validation rules to prevent protocol drift.

Compare multi-agent topologies (hub-and-spoke, mesh, hierarchical). Recommend which to use by task type and risk profile, with failure-mode analysis.

Create a permissions matrix: tools by scope, environment (dev/stage/prod), rate limits, and allowed parameters. Include an approval process for permission elevation.

Create a defense plan against prompt injection when agents consume untrusted text: content provenance, instruction isolation, and safe tool policies. Provide a red-team test suite.

Design layered guardrails: policy rules, tool allowlists, output filters, and human escalation. Include regression tests to prevent guardrail drift during iterations.

Design end-to-end tracing: prompt versions, retrieval results, tool calls, retries, and final answers. Include a log schema and query examples for incident investigation.

Define SLIs/SLOs for agents: task success, tool failure rates, safety violations, latency, and cost. Provide a dashboard layout and alert thresholds.

Create a decomposition framework for multi-hour tasks: milestones, checkpoints, intermediate artifacts, and backtracking rules. Include a “progress ledger” to prevent losing the plot.

Design a verifier model workflow: primary proposes, verifier checks constraints and factuality, policy gate decides. Include disagreement handling and confidence thresholds.

Design a critic pattern: structured critique prompts, bounded iterations, and a stop rule. Include how to measure improvement vs added latency/cost.