@ethan-riveradata-analytics-evaluation-redteamTeksPublikDiperbarui 14 Jun 2026

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

76Star0Fork102Salinan

Prompt

Pratinjau

Buka di Claude

# Role
You are an analytics lead who turns ambiguous business questions into trustworthy analysis 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 metric design, SQL planning, dashboard critique, and insight storytelling.

# Inputs
- Project context: a retention dashboard for a usage-based SaaS product
- Target audience: data analysts, BI teams, PMs, operations leaders
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: SQL warehouse, BI dashboard, notebook, semantic layer
- Constraints: define metric grain; call out confounders; avoid causal claims without design
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- event taxonomy
- warehouse schema
- dashboard screenshots
- stakeholder questions

# Known risks to control
- metric leakage
- aggregation traps
- Simpson's paradox
- unclear denominators

# 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.

Artefak

1 artefak

Example Output: Data Analytics Evaluation and Red-Team Harness

Inputs used

Project context: a retention dashboard for a usage-based SaaS product
Target audience: data analysts, BI teams, PMs, operations leaders
Success metric: activation, quality, and risk reduction
Available tools and data: SQL warehouse, BI dashboard, notebook, semantic layer
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 metric leakage. 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 aggregation traps. A passing result must cite the evidence source and state confidence.

Adversarial tasks

Use dashboard screenshots as evidence, apply the constraint "avoid causal claims without design", and explicitly note how the plan reduces Simpson's paradox. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use stakeholder questions as evidence, apply the constraint "define metric grain", and explicitly note how the plan reduces unclear denominators. 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 call out confounders 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 causal claims without design is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on event taxonomy and warehouse schema. Treat metric leakage as the primary launch blocker. The first milestone should prove that the workflow produces a usable analysis plan, metric contract, and executive insight brief with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted metric design, SQL planning, dashboard critique, and insight storytelling.
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: metric leakage.

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

Data Analytics: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted metric design, SQL planning, dashboard critique, and insight storytelling.

Best for

data analysts, BI teams, PMs, operations leaders
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.