@rin-cooperaudio-voice-executive-decision-memoTextÖffentlichAktualisiert am 14.06.2026

Audio Voice prompt that creates an executive memo that makes tradeoffs explicit and returns one-page recommendation, options table, risks, and next actions.

AI Workflow Audio Conversation Support Voice

63Stars0Fork144Kopien

Prompt

Vorschau

In ChatGPT öffnen

# 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
Create an executive memo that makes tradeoffs explicit 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. Lead with the decision
2. State assumptions and confidence
3. Compare options on the same criteria
4. End with named owners and dates

# Required output sections
1. Decision needed
2. Recommendation
3. Options
4. Evidence
5. Risks
6. Next actions

# 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.

Artefakte

1 Artefakte

Example Output: Audio Voice Executive Decision Memo

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

one-page recommendation, options table, risks, and next actions

Decision needed

The immediate decision is whether a realtime voice support agent for onboarding new SaaS customers is mature enough for a controlled pilot. The strongest evidence should come from call transcripts and voice personas; if either source is missing, mark the recommendation as provisional rather than filling the gap with assumptions.

Recommendation

Recommendation: run a narrow pilot before broad rollout. Prefer a governance-forward pilot if evidence suggests long turns; prefer a speed-forward pilot only when voice personas and fallback logs are already reliable.

Options

Option A optimizes speed by shipping a limited workflow around fallback logs. Option B optimizes control by adding reviewer sign-off and rollback steps. Option C waits until evidence from latency metrics is stronger. Use the same success metric for all three options.

Evidence

Evidence to trust: latency metrics, call transcripts, and reviewer notes from QA rubric. Evidence to treat cautiously: anecdotes that are not tied to a time window, cohort, or source owner.

Risks

Treat uncanny tone as a launch blocker until there is a control that can be verified. The minimum control is: low-latency phrasing, plus reviewer sign-off for ambiguous outputs.

Next actions

Next actions: validate voice personas, assign a reviewer for long turns, and schedule a decision checkpoint after the first pilot cohort. Do not expand scope until the review path works in practice.

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: Decision needed, Recommendation, Options, Evidence, Risks, Next actions.
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: Executive Decision Memo

Use this prompt when you need one-page recommendation, options table, risks, and next actions 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.