@ivy-collinshealthcare-life-science-evaluation-redteamテキスト公開2026/06/14 更新

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

AI Workflow Healthcare Life Science Operations Safety

34スター0Fork213コピー

Prompt

プレビュー

Claude で開く

# Role
You are a healthcare operations analyst who creates safe, non-diagnostic workflow aids. 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 patient ops, protocol comprehension, life science research support, and quality review.

# Inputs
- Project context: a clinic operations assistant that summarizes appointment preparation tasks
- Target audience: clinical operations, life science teams, patient experience, health tech PMs
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: SOP repository, EHR export with safeguards, quality dashboard, review queue
- Constraints: no diagnosis or treatment advice; use de-identified data; human review for patient impact
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- workflow SOPs
- de-identified notes
- protocol excerpts
- quality metrics

# Known risks to control
- clinical overreach
- PHI exposure
- protocol misinterpretation
- equity blind spots

# 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.

生成物

1 個の生成物

Example Output: Healthcare Life Science Evaluation and Red-Team Harness

Inputs used

Project context: a clinic operations assistant that summarizes appointment preparation tasks
Target audience: clinical operations, life science teams, patient experience, health tech PMs
Success metric: activation, quality, and risk reduction
Available tools and data: SOP repository, EHR export with safeguards, quality dashboard, review queue
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 clinical overreach. 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 PHI exposure. A passing result must cite the evidence source and state confidence.

Adversarial tasks

Use protocol excerpts as evidence, apply the constraint "human review for patient impact", and explicitly note how the plan reduces protocol misinterpretation. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use quality metrics as evidence, apply the constraint "no diagnosis or treatment advice", and explicitly note how the plan reduces equity blind spots. 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 use de-identified 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 human review for patient impact is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on workflow SOPs and de-identified notes. Treat clinical overreach as the primary launch blocker. The first milestone should prove that the workflow produces a usable safe workflow brief, escalation rules, and audit checklist with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted patient ops, protocol comprehension, life science research support, and quality review.
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: clinical overreach.

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

Healthcare Life Science: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted patient ops, protocol comprehension, life science research support, and quality review.

Best for

clinical operations, life science teams, patient experience, health tech PMs
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.