Skip to content
How I AIHow I AI

The exact AI playbook (MCPs, GPTs, Granola) that saved ElevenLabs $100k+ & helps them ship daily

Luke Harries, Head of Growth at ElevenLabs, the leading AI voice technology company, shares how he’s automating marketing workflows with AI—from case studies to translations to WhatsApp integrations—saving his company over $140,000 while making everything a launch. *What you’ll learn:* 1. How to create polished case studies in minutes using AI transcription and a custom GPT 2. How ElevenLabs built a custom AI translation system that saved them $140,000 annually and eliminated agency headaches 3. How to use Model Context Protocols (MCPs) to connect AI assistants to your WhatsApp messages 4. The “everything is a launch” philosophy that helps ElevenLabs maintain consistent marketing momentum 5. Why marketers should learn to code with AI tools like Cursor 6. How to create effective custom GPTs by focusing on prompt engineering rather than output editing *Brought to you by:* Orkes—The enterprise platform for reliable applications and agentic workflows: https://www.orkes.io/ Retool—AI that’s designed for developers, and built for the enterprise: https://retool.com/howiai *Where to find Luke Harries:* Website: https://harries.co/ LinkedIn: https://www.linkedin.com/in/luke-harries/ GitHub: https://github.com/lharries X: https://x.com/lukeharries *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo *In this episode, we cover:* (00:00) Intro (02:41) The future of AI in marketing (04:22) Using Granola and custom GPTs to write case studies (12:10) Generating tweet threads using ChatGPT (13:58) Building case studies into a systematic workflow (15:14) Best practices for prompt engineering (19:39) Building a custom translation system that saved $140k (25:10) Open sourcing the translation solution (29:47) Building a WhatsApp MCP (38:07) Creating specialized AI agents on demand (41:08) Lightning round and final thoughts *Tools referenced:* • Granola: https://www.granola.ai/ • ChatGPT: https://chat.openai.com/ • Cursor: https://www.cursor.com/ • Claude: https://claude.ai/ • ElevenLabs: https://elevenlabs.io/ • WhatsApp: https://www.whatsapp.com/ • GitHub: https://github.com/ • Zapier: https://zapier.com/ • Calendly: https://calendly.com/ • Salesforce: https://www.salesforce.com/ *Other references:* • MCP (Model Context Protocol): https://www.anthropic.com/news/model-context-protocol • WhatsApp MCP repo: https://github.com/lharries/whatsapp-mcp • Whatsmeow library: https://github.com/tulir/whatsmeow • LaunchDarkly: https://launchdarkly.com/ • Introducing ElevenLabs MCP: https://elevenlabs.io/blog/introducing-elevenlabs-mcp • Ordering a pizza using the ElevenLabs MCP server: https://x.com/elevenlabsio/status/1909300782673101265 • Chess.com: https://www.chess.com/ • Lovable: https://lovable.ai/ • v0: https://v0.dev/ • Figma: https://www.figma.com/ • Launch and launch again — how to launch your products: https://harries.co/launch-your-product • Your first growth hire: https://harries.co/first-growth-hire _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Luke HarriesguestClaire Vohost
Jun 1, 202544mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

ElevenLabs’ AI marketing playbook: automated launches, localization savings, WhatsApp MCPs

  1. Luke Harries (Head of Growth at ElevenLabs) shares three practical AI workflows that make marketing execution faster, cheaper, and more systematic: automated case studies, in-house localization, and an MCP-based WhatsApp assistant.
  2. He demonstrates a “case study in minutes” pipeline using Granola transcripts plus a custom ChatGPT “Copy Editor” GPT trained on ElevenLabs’ tone, formatting rules, and examples—then repurposes outputs into tweet threads and other launch assets.
  3. He describes ripping out a $40k/year localization SaaS plus $100k+ in agency spend by building a lightweight translation server + GitHub Action with per-language prompts, keeping human review only for sensitive pages.
  4. Finally, he explains MCPs (Model Context Protocol) and shows an unofficial WhatsApp MCP that downloads chats to a local SQLite DB so Claude can summarize, search, and message—hinting at a future personal assistant built on WhatsApp, email, and calendar.

IDEAS WORTH REMEMBERING

5 ideas

Automate the launch checklist, not just the copy.

ElevenLabs treats each feature as a full launch with value props, messaging, audience, and distribution assets. AI can compress this workflow—from draft assets to channel-specific variants—so shipping software doesn’t outpace shipping go-to-market.

Use transcripts + summaries together to avoid “lossy” content.

Luke pastes both Granola’s structured summary and the raw transcript into the GPT. The summary provides clarity and key points; the raw transcript preserves authentic customer quotes and nuance.

The best editing happens in the prompt, not the output.

When outputs miss the mark (weak headings, not enough stats, wrong format), they update the underlying instructions so every future run improves. This turns one-off fixes into compounding workflow quality.

A custom GPT is a scalable brand voice enforcement layer.

Their “ElevenLabs Copy Editor” encodes tone (serious, research-led), style rules (American English), and formatting requirements, backed by strong example posts/tweets. This makes marketing output more consistent across the team.

Distribution is part of the asset—generate it as a system.

Luke pairs creation with a repeatable workflow (e.g., Zapier trigger from “Closed Won” → Calendly → interview → transcript → GPT → publish + social). The goal is sustained throughput (e.g., “five case studies a month”), not occasional content bursts.

WORDS WORTH SAVING

5 quotes

When you're editing, as much as possible, try and edit the underlying prompt rather than the actual output.

— Luke Harries

This saved us $40,000 a year for the tool, so immediately canceled it. Over $100,000 in agency costs.

— Luke Harries

If we're just using ChatGPT for the reference of what's better, why don't we just use ChatGPT for the whole thing?

— Luke Harries

What an MCP is, it's a Model Context Protocol... which enables anyone to expose tools to AI agents.

— Luke Harries

I think a personal AI assistant really only needs your WhatsApp, your calendar, and your email, and then it knows everything about you.

— Luke Harries

“Everything is a launch” growth philosophyGranola → custom GPT case-study pipelinePrompt engineering: roles, must-do rules, examplesRepurposing: blog → X thread → LinkedIn → founder voiceBuild vs buy for SaaS tooling; marketers using CursorPrompt-driven localization via GitHub Actions + CMS buttonMCPs: tool exposure, local context, agentic workflows

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome