@kai-nakamuraai-agents-agent-system-blueprintテキスト公開2026/06/14 更新

AI Agents prompt that designs a production-ready agent system and returns agent architecture, tool contract, memory policy, eval plan, and launch guardrails.

35スター0Fork153コピー

Prompt

プレビュー

ChatGPT で開く

# Role
You are an agent architect who designs tool-using systems with evals, memory, and guardrails. You know current AI product patterns: tool calling, structured outputs, long-context reasoning, multimodal generation, MCP connectors, evals, trace review, and human approval gates.

# Mission
Design a production-ready agent system for production agent workflows, tool calling, MCP connectors, and evaluation loops.

# Inputs
- Project context: a research assistant agent that searches, cites, and drafts market briefs
- Target audience: AI engineers, platform teams, automation builders
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: MCP servers, workflow engine, trace viewer, eval runner
- Constraints: least-privilege tool access; observable decision points; human review for high-risk actions
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- tool schemas
- user tasks
- failure logs
- eval traces

# Known risks to control
- tool overuse
- unbounded loops
- stale memory
- silent failure

# Method
1. Identify the smallest autonomous loop
2. Define tool boundaries and human-review points
3. Add evals for task success, safety, and cost
4. Specify telemetry for debugging

# Required output sections
1. Use case framing
2. Agent responsibilities
3. Tools and permissions
4. Memory and context
5. Evals and guardrails
6. Rollout plan

# Output contract
Return Markdown only.
Use concise headings, decision tables, and checklists.
Every recommendation must tie back to evidence, assumptions, or a missing-input note.

# Quality bar
- Make the output reusable by another practitioner without extra explanation.
- Separate facts, assumptions, and recommendations.
- Use variables and placeholders only where the user must fill in project-specific information.
- Ask at most 3 clarifying questions only if missing information would materially change the result.
- Do not invent private facts, metrics, laws, integrations, or user quotes.
- Prefer specific operational language over generic AI enthusiasm.
- Include a "Verification" subsection when the output could affect users, money, security, compliance, health, or public trust.
- If the task involves tools or automation, state which actions are read-only, which actions write data, and which actions require human approval.

生成物

1 個の生成物

Example Output: AI Agents Agent System Blueprint

Inputs used

Project context: a research assistant agent that searches, cites, and drafts market briefs
Target audience: AI engineers, platform teams, automation builders
Success metric: activation, quality, and risk reduction
Available tools and data: MCP servers, workflow engine, trace viewer, eval runner
Desired depth: Production-ready
Output tone: Clear operator memo

Generated Result

agent architecture, tool contract, memory policy, eval plan, and launch guardrails

Use case framing

The immediate decision is whether a research assistant agent that searches, cites, and drafts market briefs is mature enough for a controlled pilot. The strongest evidence should come from tool schemas and user tasks; if either source is missing, mark the recommendation as provisional rather than filling the gap with assumptions.

Agent responsibilities

The AI system may draft agent architecture, tool contract, memory policy, and eval suite, summarize user tasks, and propose next actions. It must not make irreversible changes, approve high-impact decisions, or treat unverified assumptions as facts.

Tools and permissions

Use trace viewer as the primary working surface. Read actions are allowed by default; write actions require an explicit human approval step and an audit entry containing source, reviewer, and rollback path.

Memory and context

Persist only durable preferences, approved terminology, and stable project constraints. Do not store private user data, transient metrics, or unresolved claims from eval traces.

Evals and guardrails

Create at least 12 golden tasks: 6 normal cases, 3 edge cases, and 3 adversarial cases targeting tool overuse. A passing result must cite the evidence source and state confidence.

Rollout plan

Release in three gates: internal dry run, limited pilot, then measured expansion. Each gate must show evidence that human review for high-risk actions is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on tool schemas and user tasks. Treat tool overuse as the primary launch blocker. The first milestone should prove that the workflow produces a usable agent architecture, tool contract, memory policy, and eval suite with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to production agent workflows, tool calling, MCP connectors, and evaluation loops.
It includes the required sections: Use case framing, Agent responsibilities, Tools and permissions, Memory and context, Evals and guardrails, Rollout plan.
It separates evidence, assumptions, risks, and recommended next actions.
It includes practical verification steps, not only generic advice.
It names the most important failure mode for this domain: tool overuse.

Reuse note

Before copying the output into production work, replace all default variables with your real data and run a human review for high-impact decisions.

README

README.md

AI Agents: Agent System Blueprint

Use this prompt when you need agent architecture, tool contract, memory policy, eval plan, and launch guardrails for production agent workflows, tool calling, MCP connectors, and evaluation loops.

Best for

AI engineers, platform teams, automation builders
Teams that already have partial context but need a sharper, reusable artifact
AI workflows where the output must be auditable, editable, and easy to hand off

How to use

Replace the variables in the prompt with your real project context.
Keep the default constraints unless your team has stronger internal rules.
Review the generated output against the checklist in the example artifact.

Design notes

This seed follows current prompting practice: explicit role, structured inputs, domain evidence, operational guardrails, and a concrete output contract. It is written in English for international PromptHub users.