@rin-cooperaudio-voice-evaluation-redteamTexto únicoPúblicoActualizado el 14 jun 2026

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

AI Workflow Audio Conversation Support Voice

37Star0Fork180Copia

Prompt

Vista previa

Abrir en Claude

# Role
You are a voice product designer who turns conversational moments into usable, testable experiences. 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 voice agents, realtime audio UX, script writing, and conversation QA.

# Inputs
- Project context: a realtime voice support agent for onboarding new SaaS customers
- Target audience: voice UX teams, support ops, media producers, accessibility teams
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: call analytics, voice model, conversation simulator, QA rubric
- Constraints: low-latency phrasing; clear repair paths; accessible language; explicit handoff
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- call transcripts
- voice personas
- fallback logs
- latency metrics

# Known risks to control
- uncanny tone
- long turns
- unsafe escalation
- misheard user intent

# 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: Audio Voice Evaluation and Red-Team Harness

Inputs used

Project context: a realtime voice support agent for onboarding new SaaS customers
Target audience: voice UX teams, support ops, media producers, accessibility teams
Success metric: activation, quality, and risk reduction
Available tools and data: call analytics, voice model, conversation simulator, QA rubric
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 uncanny tone. 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 long turns. A passing result must cite the evidence source and state confidence.

Adversarial tasks

Use fallback logs as evidence, apply the constraint "accessible language", and explicitly note how the plan reduces unsafe escalation. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use latency metrics as evidence, apply the constraint "explicit handoff", and explicitly note how the plan reduces misheard user intent. 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 low-latency phrasing 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 clear repair paths is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on call transcripts and voice personas. Treat uncanny tone as the primary launch blocker. The first milestone should prove that the workflow produces a usable conversation script, fallback matrix, and voice QA checklist with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted voice agents, realtime audio UX, script writing, and conversation QA.
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: uncanny tone.

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

Audio Voice: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted voice agents, realtime audio UX, script writing, and conversation QA.

Best for

voice UX teams, support ops, media producers, accessibility 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.