Step01
Capture Meeting Data
Select a representative, authorized transcript set across teams, meeting types, and time periods. Document who and what is included, remove unnecessary sensitive material, and limit access to the analysis.
BeginnerOperations
How to Use AI to Define Your Unspoken Company Culture with Granola
Use an authorized set of meeting transcripts to surface how the company actually makes decisions, then review the evidence and convert durable behaviors into a practical hiring rubric.
Source episode · 07:00
How I AI: Zapier CEO Wade Foster's Playbook for AI-Powered Recruiting and Culture Buildingwith Claire Vo
Wade runs Granola’s unspoken-company-culture recipe across his meeting history, compares the observed behaviors with Zapier’s stated values, and turns the result into interview criteria.
Before you start
What you need
- An authorized set of representative meeting transcripts
- Granola or another meeting-analysis tool
- The company’s stated values and existing hiring criteria
- Owners for culture and people operations
What you’ll make
A reviewed culture handbook that separates observed behavior from interpretation and supplies job-relevant examples for interview rubrics and coaching.
Tools used
- ChatGPTVisitChatGPT
OpenAI conversational AI
- Granola
AI-powered meeting note-taker and summarizer
Step by step
The workflow
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Step02
Run the 'Unspoken Culture' Recipe
Run Granola’s unspoken-company-culture recipe or an equivalent prompt. Require observed behaviors, supporting examples, tensions, and the limits of the sample.
Example prompt
Analyze these authorized meeting notes for recurring ways the company makes decisions, handles disagreement, shares context, follows through, and responds to mistakes. For each theme, provide representative evidence, counterexamples, confidence, and sample limitations. Do not infer personality traits or expose personnel details.
Step03
Analyze the AI-Generated Handbook
Compare the draft with stated values and direct participant feedback. Mark what is aligned, newly observed, inconsistent, or unsupported, and remove themes that depend on one person or meeting.
Step04
Generate a Hiring Rubric with ChatGPT
Convert the accepted themes into a hiring rubric with observable evidence, anchored rating levels, and questions that allow different backgrounds and working styles to succeed.
Example prompt
Turn these reviewed culture themes into a job-related interview rubric. For each criterion, define observable behaviors, a structured question, evidence for strong and weak answers, and anchored scores from 1 to 4. Avoid personality fit, demographic proxies, and style preferences. Flag any theme too vague to score fairly.
What good looks like
- Each cultural theme includes representative meeting evidence.
- The analysis distinguishes company-wide patterns from one leader’s meeting sample.
- Sensitive or personnel-specific material is removed from downstream assets.
- Hiring criteria describe observable job behavior rather than personality or demographic proxies.
Build your next product with ChatPRD
Turn an idea into a PRD, user stories, and a plan.
After the steps
Runbook notes
How to recover when the loop fails and where human judgment helps.
Recover
If it goes sideways
- One executive’s meetings are presented as the whole company culture
- Label the sample, add representative teams and meeting types, and keep local patterns separate from company-wide claims.
- Private personnel or customer details appear in the handbook
- Restrict transcript access, remove identifying detail, and publish only aggregated behavioral evidence.
- The model turns stated values into flattering but unsupported copy
- Require examples from meetings, disagreements, tradeoffs, and counterexamples for every theme.
- A culture trait becomes a personality or sameness screen
- Rewrite it as an observable, job-related behavior with multiple valid ways to demonstrate it.
Keep building
Related workflows
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
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
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.
Free to start
No credit card
SOC 2 certified
Enterprise ready