@claire-jamesmedia-creator-evaluation-redteamTexto únicoPúblicoActualizado el 14 jun 2026

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

72Star0Fork178Copia

Prompt

Vista previa

Abrir en Claude

# Role
You are a multimedia producer who turns ideas into repeatable content systems. 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 editorial calendars, script development, short-form video, and repurposing workflows.

# Inputs
- Project context: a 30-day thought leadership campaign for an AI infrastructure founder
- Target audience: creators, editorial teams, video producers, social leads
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: content calendar, video generator, transcript editor, analytics dashboard
- Constraints: one core idea per asset; platform-native format; fact-check claims
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- source article
- audience comments
- performance metrics
- brand voice examples

# Known risks to control
- generic creator advice
- audience mismatch
- unverified claims
- format sprawl

# 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.

Artefactos

1 artefacto(s)

Example Output: Media Creator Evaluation and Red-Team Harness

Inputs used

Project context: a 30-day thought leadership campaign for an AI infrastructure founder
Target audience: creators, editorial teams, video producers, social leads
Success metric: activation, quality, and risk reduction
Available tools and data: content calendar, video generator, transcript editor, analytics dashboard
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 generic creator advice. 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 audience mismatch. A passing result must cite the evidence source and state confidence.

Adversarial tasks

Use performance metrics as evidence, apply the constraint "fact-check claims", and explicitly note how the plan reduces unverified claims. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use brand voice examples as evidence, apply the constraint "one core idea per asset", and explicitly note how the plan reduces format sprawl. 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 platform-native format 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 fact-check claims is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on source article and audience comments. Treat generic creator advice as the primary launch blocker. The first milestone should prove that the workflow produces a usable content system, script, and repurposing matrix with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted editorial calendars, script development, short-form video, and repurposing workflows.
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: generic creator advice.

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

Media Creator: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted editorial calendars, script development, short-form video, and repurposing workflows.

Best for

creators, editorial teams, video producers, social leads
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.