Prompt Cards

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.

Create an A2A negotiation mechanism: task contracts, acceptance criteria, SLAs, and cost budgets. Include how agents refuse tasks they cannot verify or safely perform.

Design MCP tool schemas: typed inputs/outputs, explicit error codes, idempotency rules, and logging fields. Provide examples of good vs bad schema design for agent reliability.

Create a sandbox model for tool execution: network isolation, file access boundaries, rate limits, and safe parameter validation. Include a threat model and tests for containment failures.

Design a RAG pipeline for agents: retrieval, citation, cross-checking, and contradiction handling. Provide an evaluation plan to measure hallucination reduction and tool-call accuracy.

Create a memory architecture: scratchpad, episodic memory, semantic memory, and “facts of record.” Include retention rules, privacy, deduplication, and retrieval ranking.

Design a planner–executor split: planner produces a verifiable plan, executor performs bounded actions, verifier checks constraints. Include gate criteria, rollback triggers, and audit logging.

Design an agent-to-agent (A2A) coordination protocol: message types, handoffs, escalation rules, and consensus patterns. Include how to prevent loops, duplication, and hallucinated delegation.

Create an MCP-first design: define servers, tools, schemas, and a permission model. Provide naming conventions, versioning, and a “deny-by-default” policy for tool exposure.

Design a high-capability agent architecture (marketed as “IQ150-level”) that stays reliable: modular planner/executor, tool sandboxing, and human-in-the-loop gates. Include a component diagram, data flows, and failure-mode mitigations.

Create a 90-day implementation plan for a safe recursive improvement system: milestones, deliverables, tests, monitoring, governance, and a pilot rollout. Include a ‘pause and assess’ week.