@kai-nakamuraai-agents-risk-governance-reviewTextPublicUpdated Jun 14, 2026

AI Agents prompt that reviews a workflow for operational, privacy, and safety risk and returns risk register, severity ranking, controls, and verification checklist.

19Stars0Fork146Copies

Prompt

Preview

Open in Claude

# 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
Review a workflow for operational, privacy, and safety risk 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. Trace data and permissions
2. Rank risk by likelihood and impact
3. Map every high risk to a concrete control
4. Identify who must approve residual risk

# Required output sections
1. System boundary
2. Data sensitivity
3. Risk register
4. Controls
5. Residual risk
6. Verification checklist

# 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.

Artifacts

1 artifacts

Example Output: AI Agents Risk Governance Review

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

risk register, severity ranking, controls, and verification checklist

System boundary

Use tool schemas as evidence, apply the constraint "least-privilege tool access", and explicitly note how the plan reduces tool overuse. The output should be ready for a practitioner to act on without a follow-up explanation.

Data sensitivity

Treat unbounded loops as a launch blocker until there is a control that can be verified. The minimum control is: observable decision points, plus reviewer sign-off for ambiguous outputs.

Risk register

Treat stale memory as a launch blocker until there is a control that can be verified. The minimum control is: human review for high-risk actions, plus reviewer sign-off for ambiguous outputs.

Controls

Treat silent failure as a launch blocker until there is a control that can be verified. The minimum control is: least-privilege tool access, plus reviewer sign-off for ambiguous outputs.

Residual risk

Treat tool overuse as a launch blocker until there is a control that can be verified. The minimum control is: observable decision points, plus reviewer sign-off for ambiguous outputs.

Verification checklist

Use user tasks as evidence, apply the constraint "human review for high-risk actions", and explicitly note how the plan reduces unbounded loops. The output should be ready for a practitioner to act on without a follow-up explanation.

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: System boundary, Data sensitivity, Risk register, Controls, Residual risk, Verification checklist.
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: Risk Governance Review

Use this prompt when you need risk register, severity ranking, controls, and verification checklist 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.