Step01
Obtain Call Transcript and Employee Info
Use the cleaned authorized transcript and stable employee identity from the call workflow. Confirm speaker labels and skip the coaching path when attribution is uncertain.
IntermediateSales
How to Build an Automated AI Sales Coaching System from Call Transcripts
Give sales and customer-success reps timely private coaching by comparing each call with a transparent behavior rubric, citing specific moments, and keeping development feedback separate from automated performance decisions.
Source episode · 28:00
How Suzy's CEO Turns 25,000 Hours of Sales Calls into Automated Marketing and Coaching with One Zapier Workflowwith Claire Vo
Matt generates private post-call coaching for the sales or customer-success rep, sends it directly in Slack, and stores recurring feedback themes so the employee and manager can see patterns over time.
Before you start
What you need
- Authorized transcripts with reliable speaker labels
- Employee notice and approved coaching-use policy
- A role-specific call-quality rubric
- Employee and manager directory mappings
- Private Slack delivery and governed retention rules
What you’ll make
A private coaching note with evidence-backed strengths, one focused improvement, a next-call practice, and an optional trend view controlled by the approved people process.
Tools used
- ChatGPTVisitChatGPT
OpenAI conversational AI
- ZapierVisitZapier
Workflow automation platform
Step by step
The workflow
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Step02
Prompt the AI to Act as a Coach
Compare the employee’s observable actions with a published role rubric. Ask for timestamped strengths, one high-leverage improvement, a practice for the next call, and uncertainty.
Example prompt
Act as a development coach using only this call and the attached role rubric. Evaluate observable behaviors such as discovery questions, listening, clarification, objection handling, expectation setting, and next-step ownership. Cite timestamps. Return two strengths, one priority improvement, a concrete next-call practice, and confidence. Do not evaluate personality, accent, protected traits, or employment suitability.
Step03
Send Private Feedback via Slack
Send the note privately to the employee with the source call and a way to flag transcript or attribution errors. Let the employee choose whether to share it with a manager unless policy states otherwise.
Step04
Log Performance Data for Managers
If the organization tracks trends, store only reviewed rubric categories and dates under approved retention and access rules. Show supporting calls and corrections, and prohibit automated ratings, discipline, or compensation actions.
This historical log makes performance reviews much more objective and data-driven, allowing managers to spot patterns and identify team-wide training needs.
What good looks like
- Feedback references the correct employee and specific call moments.
- The rubric evaluates observable job behavior rather than style, identity, or protected traits.
- The employee can correct transcript or attribution errors.
- AI feedback is not used alone for ratings, discipline, compensation, or employment decisions.
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
- The model attributes the customer’s words or interruptions to the employee
- Validate diarization, cite timestamps, and suppress coaching when speaker identity is uncertain.
- Feedback penalizes accent, personality, disability, communication style, or another protected signal
- Constrain the rubric to observable role behavior and audit patterns across comparable calls.
- Coaching is posted publicly or retained beyond the approved purpose
- Use private delivery, role-based access, a retention period, and a correction or deletion path.
- Generated notes become an unreviewed performance dossier
- Separate development coaching from HR records and require the approved human process for consequential use.
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