By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.
Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
Great conversations run long. Their best ideas don't have to.
uListen is free on iPhone, iPad, Android, Chrome, and Claude.
See howEpisode Details
EPISODE INFO
- Released
- November 13, 2026
- Duration
- 58m
- Channel
- Aakash Gupta
- Watch on YouTube
- ▶ Open ↗
EPISODE DESCRIPTION
Greg Greiner ran product at Bolt. Now he's co-founder and CEO of Woven, and in this episode he builds an AI research agent in Claude Code that emails every customer who drops off your funnel, then adds an eval loop live so the agent can reply without you. He also explains why one PM can now run a team that ships like 25 engineers. Full Writeup: https://www.news.aakashg.com/p/ai-customer-research Transcript: https://www.aakashg.com/how-to-talk-to-every-one-of-your-customers-with-ai/ Timestamps 0:00 - Intro 1:36 - What AI research on every drop-off can tell you 6:32 - How to build your own research agent in Claude Code 7:00 - Ads 8:52 - Demo: an agent that emails customers who drop off 12:29 - Why email beats in-app chat, and 20% to 40% reply rates 16:03 - The four emails to send across the customer journey 24:15 - Adding an eval loop to the agent, live 31:23 - What Woven adds, and when to talk to customers yourself 35:46 - The full AI research agenda for a PM 40:28 - Why one PM can now run a team that ships like 25 engineers 45:45 - AI for your team vs AI for your customers 52:03 - Inside an AI-native startup, from whiteboard to PRD 🏆 Thanks to our sponsors:
1. Jira Product Discovery: Plan with purpose, ship with confidence - https://www.atlassian.com/software/jira/product-discovery?utm_source=aakash_gupta&utm_medium=referral Key Takeaways
1. Go from seven customer conversations a month to thousands - At Bolt, Greg "would have been happy to talk to seven or eight customers a month." AI now holds those back-and-forth conversations with thousands of customers.
1. Split every concern into a messaging fix or a product fix - Shipping questions convert once the AI answers them. Fix those with messaging. Subscription confusion doesn't convert even after the AI responds, so that one is a product problem.
1. Email the customers who already left - Someone who abandoned isn't in your app anymore, and a research chat inside the app can hurt conversion for people who haven't decided yet. Email is "a channel that all of your customers already use daily," which is why Greg's research campaigns get 20% to 40% reply rates, and a fitness company saw about 35% trial abandonment.
1. Ask one simple question per email - The common mistake is trying to "recreate your survey maybe in one email." Ask one short, direct question and let the customer lead.
1. Put your emails where people drop off - Start at the widest part of the funnel, people who entered an email and never finished signing up. Few of them reply. It's still your biggest group. When a trial ends without converting, offer something like 20% off just for feedback. Greg says that "massively increases reply rate," and the people who reply are the ones already on the fence.
1. Build the agent in Claude Code in under an hour - Greg's demo runs on a CSV of customers and a few markdown files about the company, and it sends through the Gmail MCP. The first pass broke reply threading, but it worked within 30 to 40 minutes. Keep replies fast. When Woven tested adding delays, reply rates dropped "precipitously."
1. Add an eval loop with one prompt - Greg asked Claude Code to check auto-sent replies for "groundedness in the documentation" and to save a fresh draft when one fails. Feed the failure into a full rerun, or you'll overfit.
1. Test customer-facing AI in a sandbox first - An internal tool can live with a lower bar, because a person reviews it first. Even a model upgrade on customer-facing AI means running trusted sample data outside production and checking that guardrails pass at the same rate as before. LLM judges want to please too, so make yours link every action in a reply to the instruction that allowed it.
1. One PM can now run a team that ships like 25 engineers - Greg's most productive stretch at Uber was one PM to about 25 engineers. Now three to five engineers ship that much, and the PM keeps it all "greater than the sum of its parts."
1. Spend your time deciding what to build - At Woven, a team of four, building fast with good quality is the easy part. "What's hard is still building the right thing." So the team debates the problem at a whiteboard while recording, then feeds the transcript and the diagram to an AI skill that writes the PRD and the Linear tasks. It only works if everyone at the table has a baseline of product and business sense. 👨💻 Where to find Greg Greiner LinkedIn: https://www.linkedin.com/in/greggreiner1/ Woven: https://woven.ai/ 👨💻 Where to find Aakash Twitter: https://x.com/aakashgupta LinkedIn: https://www.linkedin.com/in/aagupta/ Newsletter: https://www.news.aakashg.com 🧠 About Product Growth The world's largest podcast focused solely on product + growth, with over 200K+ listeners. You can also catch it on Apple Podcasts: https://podcasts.apple.com/us/podcast/the-growth-podcast/id1763555775 Spotify: https://open.spotify.com/show/7vVEMqCSKb7I7xPk8xZtg5 🔔 Subscribe and turn on notifications for more videos like this.
SPEAKERS
Greg Greiner
guestFormer CPO at Bolt and product leader (including Uber for Business), now CEO building AI-agent workflows for customer research.
Aakash Gupta
hostHost of Product Growth with Aakash Gupta; product/growth leader and newsletter author focused on AI and product management.
EPISODE SUMMARY
In this episode of Aakash Gupta, featuring Greg Greiner and Aakash Gupta, How to Talk to 100,000 Customers with AI (Ex-Bolt CPO) explores Use Claude Code to scale churn research via email agents Greg Greiner argues AI makes it possible for PMs to run personalized back-and-forth customer conversations at massive scale and turn them into recurring insights.
RELATED EPISODES
