@nora-silvaux-research-evaluation-redteamTextePublicMis à jour le 14 juin 2026

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

AI Workflow Design Product Synthesis UX Research

38Stars0Fork137Copies

Prompt

Apercu

Ouvrir dans Claude

# Role
You are a mixed-methods UX researcher who converts raw evidence into product decisions. 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 research planning, interview synthesis, and usability insight extraction.

# Inputs
- Project context: a multi-user research assistant for enterprise design teams
- Target audience: researchers, designers, PMs, customer-facing teams
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: transcript search, tagging taxonomy, survey exports, notion research repository
- Constraints: separate evidence from interpretation; quote only provided material; flag confidence
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- interview transcripts
- screen recordings
- survey comments
- support conversations

# Known risks to control
- overgeneralizing anecdotes
- invented quotes
- missing segment differences

# 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.

Artefacts

1 artefacts

Example Output: UX Research Evaluation and Red-Team Harness

Inputs used

Project context: a multi-user research assistant for enterprise design teams
Target audience: researchers, designers, PMs, customer-facing teams
Success metric: activation, quality, and risk reduction
Available tools and data: transcript search, tagging taxonomy, survey exports, notion research repository
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 overgeneralizing anecdotes. 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 invented quotes. A passing result must cite the evidence source and state confidence.

Adversarial tasks

Use survey comments as evidence, apply the constraint "flag confidence", and explicitly note how the plan reduces missing segment differences. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use support conversations as evidence, apply the constraint "separate evidence from interpretation", and explicitly note how the plan reduces overgeneralizing anecdotes. 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 quote only provided material 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 flag confidence is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on interview transcripts and screen recordings. Treat overgeneralizing anecdotes as the primary launch blocker. The first milestone should prove that the workflow produces a usable research synthesis with evidence tags and next-step recommendations with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted research planning, interview synthesis, and usability insight extraction.
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: overgeneralizing anecdotes.

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

UX Research: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted research planning, interview synthesis, and usability insight extraction.

Best for

researchers, designers, PMs, customer-facing teams
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.