Turn an authorized customer interview into a source grounded case study by combining the transcript and notes with a versioned editorial prompt, then verify quotes, outcomes, product claims, links, and customer permission before repurposing the story.
Source episode · 04:00
How I AI: 3 AI Workflows to Save $140K & Automate Marketing with ElevenLabs' Luke Harrieswith Claire Vo
Luke records a short customer interview in Granola, asks for concrete use and impact details, gives a custom ElevenLabs copy editor GPT both the summary and raw transcript, generates a case study and social post in the company voice, then improves recurring problems in the underlying GPT instructions.
A draft case study and channel specific derivatives whose claims and quotations trace to the interview, whose metrics include context, and whose approved final version is recorded before publication.
OpenAI conversational AI
Workflow automation platform
AI-powered meeting note-taker and summarizer
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Confirm recording, transcription, attribution, logo, quote, publishing, and reuse expectations before the call. Use an interview guide that asks for concrete workflow, before state, implementation, results, evidence, and limitations.
Build a custom editor with the company voice, case study structure, product facts, approved links, strong examples, banned claims, and rules for quotes, metrics, missing evidence, and customer review.
Act as an editor for [company] case studies. Use only supplied interview and approved product facts. Preserve exact quotes with timestamps, label estimates, and mark unsupported details [VERIFY]. Follow this structure and voice guide: [guide]. Never invent metrics, customer intent, product capabilities, pricing, or links.
Provide both the Granola summary and raw transcript. Ask for a source table before prose, then draft the story around the customer problem, use, implementation, result, and what remains imperfect.
From this summary and transcript, create a source table of candidate claims and quotes with speaker and timestamp. Flag conflicts and missing context. Then draft a case study using only supported material, with [VERIFY] placeholders for unresolved facts. Summary: [summary]. Transcript: [transcript].
Create social and sales versions only from the approved case study. Preserve qualifiers and links, adapt length to the channel, and do not manufacture a stronger hook than the evidence supports.
write a tweet thread for this
If recurring edits appear, update and test the underlying editor instructions against a small regression set. Keep customer specific drafting, factual review, customer approval, and publishing as explicit tracked states in the content workflow.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
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.
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.
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.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.