←Back/Sales/Claude
IntermediateSales

How to Build an AI Communication Coach for Stakeholder Management Using Claude

Prepare for a difficult stakeholder conversation by giving Claude the situation, people, evidence, constraints, and selected communication references, then use its output to rehearse questions and options without stereotyping colleagues or outsourcing judgment.

How to Build an AI Communication Coach for Stakeholder Management Using Claude

Source episode · 27:00

How Prerna Kaul Automates 60,000-Page FDA Submissions and Coaches PMs with AI

with Claire Vo

Prerna uses Anthropic's prompt generator and optimizer to create a Claude Project for influence and communication, loads selected writing and persuasion references, gives it a difficult stakeholder scenario, and receives tailored one on one questions, a leadership meeting plan, and likely curveballs.

Read the full episodeWatch on YouTubeListen on SpotifyListen on Apple

Before you start

What you need

  • A specific upcoming decision, meeting, or conflict
  • Confirmed stakeholder roles, stated concerns, incentives, constraints, and prior decisions
  • Approved reference material on communication, negotiation, ethics, and domain obligations
  • A privacy safe description that excludes unnecessary personal or confidential details
  • The desired meeting outcome, nonnegotiables, open questions, and fallback options

What you’ll make

A practical preparation brief with stakeholder specific questions, shared facts, areas of disagreement, options, meeting sequence, likely objections, and language the user has reviewed and can deliver authentically.

Tools used

Step by step

The workflow

Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.

5 steps

Step01

Craft the Master Prompt

Use the prompt generator to structure the coach around one decision. Include known facts, stakeholder statements, ethical and policy constraints, desired outcome, and rules against invented motives, while requiring questions and alternatives rather than a single persuasive script.

Example prompt
Help me prepare for [decision or meeting]. Known facts: [facts]. Stakeholders and their stated concerns: [statements]. Constraints and obligations: [constraints]. Desired outcome and nonnegotiables: [details]. Separate facts from hypotheses, do not infer motives from identity or title, and propose ethical questions and options rather than manipulation.
Step02

Train Your Coach with a Knowledge Base

Load a small, permitted knowledge base with communication frameworks, domain policy, and examples you trust. Record title, author, edition, relevance, and limits, and tell Claude to cite the specific principle it applies.

Step03

Simulate a High-Stakes Scenario

Describe the current scenario with a decision deadline, evidence, disagreements, dependencies, and what changed. Anonymize unnecessary details and ask the coach to identify missing perspectives or facts before recommending a sequence.

Example prompt
Analyze this scenario: [scenario]. Return confirmed facts, each stakeholder's stated concern, unknowns, missing participants, power or policy constraints, and questions to resolve before deciding. Do not draft persuasive language yet.
Step04

Generate a Comprehensive Strategic Playbook

Generate a preparation brief with individual conversations, shared framing, options, meeting agenda, decision method, and follow up. For each recommendation, cite the relevant fact or communication principle and state what new evidence would change it.

Step05

Prepare for Curveball Questions

Ask for likely objections and hard questions from each role, then rehearse concise truthful responses. Replace generic scripts with your own language and prepare to acknowledge uncertainty, pause, or change direction when the meeting reveals new facts.

Example prompt
Challenge this plan from the perspective of each stakeholder using only their stated concerns and role obligations. Ask the hardest likely questions, identify weak evidence, and suggest concise responses that acknowledge uncertainty. Include conditions under which I should change the proposal or defer the decision.

What good looks like

  • The coach distinguishes what a stakeholder actually said from assumptions about motive or personality.
  • Recommendations respect ethics, policy, power dynamics, and domain obligations rather than optimizing only for persuasion.
  • Each suggested conversation has a purpose, questions to ask, evidence to bring, and decisions to record.
  • The user rehearses likely objections, adapts the language to their own voice, and remains open to new information in the meeting.

Build your next product with ChatPRD

Turn an idea into a PRD, user stories, and a plan.

Try ChatPRD free

After the steps

Runbook notes

How to recover when the loop fails and where human judgment helps.

Recover

If it goes sideways

The model invents motives or communication preferences from title, identity, or personality labels
Use only observed statements and constraints, mark hypotheses, and begin with questions that let the stakeholder correct the model.
Advice prioritizes winning or pressure over an ethical and durable decision
Require transparent intent, shared evidence, legitimate interests, and respect for policy and power differences.
The scenario exposes confidential personnel, health, customer, or company information
Minimize and anonymize details, use an approved workspace, and keep sensitive evidence in its source system.
A polished script sounds artificial or prevents genuine listening
Convert it to goals, questions, and optional phrases, rehearse aloud, and use the live conversation to update the plan.

Keep building

Related workflows

Create a Meta-Workflow to Continuously Improve Your AI Assistant's Performance
advancedPersonalClaude

Create a Meta-Workflow to Continuously Improve Your AI Assistant's Performance

Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.

Open
Build a Self-Improving AI Morning Brief to Capture Action Items and Learn Company Jargon
intermediateProductClaudeGranola

Build a Self-Improving AI Morning Brief to Capture Action Items and Learn Company Jargon

Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.

Open
Automate Your Weekly Planning with an AI-Powered PM Assistant
intermediateProductClaudeNotion+1

Automate Your Weekly Planning with an AI-Powered PM Assistant

Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.

Open

Start shipping
better products.

Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.

Start building freeRequest a demo
Free to start
No credit card
SOC 2 certified
Enterprise ready