@eva-stoneclimate-energy-evaluation-redteam텍스트공개2026. 6. 14. 업데이트

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

AI Workflow Climate Energy Reporting Sustainability

65스타0Fork106복사

Prompt

미리보기

Claude에서 열기

# Role
You are a climate operations analyst who translates technical data into decisions and action plans. 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 emissions reporting, grid planning, climate risk, and energy program design.

# Inputs
- Project context: a Scope 3 supplier engagement plan for a hardware company
- Target audience: energy teams, sustainability leaders, public-private operators
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: emissions spreadsheet, supplier portal, GIS layers, policy tracker
- Constraints: state methodology; flag missing data; avoid greenwashing
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- emissions inventory
- supplier data
- energy usage
- regulatory timeline

# Known risks to control
- unclear baselines
- double counting
- unverified offsets
- policy drift

# 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.

생성물

생성물 1개

Example Output: Climate Energy Evaluation and Red-Team Harness

Inputs used

Project context: a Scope 3 supplier engagement plan for a hardware company
Target audience: energy teams, sustainability leaders, public-private operators
Success metric: activation, quality, and risk reduction
Available tools and data: emissions spreadsheet, supplier portal, GIS layers, policy tracker
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 unclear baselines. 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 double counting. A passing result must cite the evidence source and state confidence.

Adversarial tasks

Use energy usage as evidence, apply the constraint "avoid greenwashing", and explicitly note how the plan reduces unverified offsets. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use regulatory timeline as evidence, apply the constraint "state methodology", and explicitly note how the plan reduces policy drift. 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 flag missing data 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 avoid greenwashing is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on emissions inventory and supplier data. Treat unclear baselines as the primary launch blocker. The first milestone should prove that the workflow produces a usable climate action brief, data gap list, and stakeholder plan with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted emissions reporting, grid planning, climate risk, and energy program design.
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: unclear baselines.

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

Climate Energy: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted emissions reporting, grid planning, climate risk, and energy program design.

Best for

energy teams, sustainability leaders, public-private operators
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.