@eli-carterpublic-policy-evaluation-redteam单文本公开更新于 2026年6月14日

Public Policy prompt that builds an evaluation suite for high-risk AI workflows and returns eval matrix, adversarial cases, grading rubric, and release threshold.

AI Governance AI Workflow Civic Tech Policy Public Sector

51收藏0Fork143复制

Prompt

预览

在 Claude 打开

# Role
You are a civic technology policy analyst who writes clear, accountable AI program materials. 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
Build an evaluation suite for high-risk AI workflows for AI-assisted policy analysis, public service workflows, community engagement, and accountability plans.

# Inputs
- Project context: a city service chatbot pilot for multilingual resident support
- Target audience: policy teams, public sector product leads, civic technologists
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: policy library, service dashboard, public comment tracker, translation QA
- Constraints: public accountability; accessibility; plain-language communication; human appeal path
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- policy text
- constituent feedback
- service metrics
- procurement constraints

# Known risks to control
- unequal access
- opaque decisions
- procurement lock-in
- policy overreach

# Method
1. Convert user outcomes into measurable tasks
2. Include realistic failure modes
3. Separate correctness from style
4. Define pass, warn, and block thresholds

# Required output sections
1. Success criteria
2. Golden tasks
3. Adversarial tasks
4. Rubric
5. Sampling plan
6. Release decision

# 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.

产物

1 个产物

Example Output: Public Policy Evaluation and Red-Team Harness

Inputs used

Project context: a city service chatbot pilot for multilingual resident support
Target audience: policy teams, public sector product leads, civic technologists
Success metric: activation, quality, and risk reduction
Available tools and data: policy library, service dashboard, public comment tracker, translation QA
Desired depth: Production-ready
Output tone: Clear operator memo

Generated Result

eval matrix, adversarial cases, grading rubric, and release threshold

Success criteria

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

Golden tasks

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

Adversarial tasks

Use service metrics as evidence, apply the constraint "plain-language communication", and explicitly note how the plan reduces procurement lock-in. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use procurement constraints as evidence, apply the constraint "human appeal path", and explicitly note how the plan reduces policy overreach. The output should be ready for a practitioner to act on without a follow-up explanation.

Sampling plan

Release in three gates: internal dry run, limited pilot, then measured expansion. Each gate must show evidence that public accountability is true in practice, not only in documentation.

Release decision

Release in three gates: internal dry run, limited pilot, then measured expansion. Each gate must show evidence that accessibility is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on policy text and constituent feedback. Treat unequal access as the primary launch blocker. The first milestone should prove that the workflow produces a usable policy brief, pilot plan, and accountability checklist with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted policy analysis, public service workflows, community engagement, and accountability plans.
It includes the required sections: Success criteria, Golden tasks, Adversarial tasks, Rubric, Sampling plan, Release decision.
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: unequal access.

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

Public Policy: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted policy analysis, public service workflows, community engagement, and accountability plans.

Best for

policy teams, public sector product leads, civic technologists
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.