Skip to content

By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.

Aakash GuptaAakash Gupta

How to Talk to 100,000 Customers with AI (Ex-Bolt CPO)

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…

Greg GreinerguestAakash Guptahost
Nov 13, 202658mWatch on YouTube

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 how

At a glance

WHAT IT’S REALLY ABOUT

Use Claude Code to scale churn research via email agents

  1. 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.
  2. He describes pairing conversation themes with conversion outcomes to determine which drop-off concerns can be addressed by messaging versus requiring deeper product fixes.
  3. He demos a lightweight build using Claude Code that pulls customer data (e.g., CSV), sends personalized emails, and replies quickly to sustain engagement and gather richer feedback.
  4. He explains why email is effective for abandoned users and outlines lifecycle email touchpoints—from incomplete signup through trial drop-off to churn—sometimes pairing outreach with incentives to increase responses.
  5. He connects these workflows to a broader shift in PM work: fewer process-heavy rituals, higher output velocity, and stronger quality systems (guardrails/evals/sandbox testing) for any AI that talks directly to customers.

IDEAS WORTH REMEMBERING

5 ideas

AI enables “scaled research” by automating personalized, two-way customer conversations.

Greg Greiner says AI can create a “scaled representation” of a PM that proactively reaches out, holds back-and-forth conversations, and returns recurring insights to the team, turning customer research into a continuous, scalable system.

Pair conversation insights with conversion data to prioritize what to fix.

Using an example of users abandoning a purchase flow, Greg explains how you can segment what concerns come up most, then compare not only frequency but also downstream conversion behavior after the AI conversation to see which issues are “messaging-fixable” versus structural product problems.

Email is a high-leverage channel for researching and recovering drop-offs.

Greg argues email is particularly effective for abandoned audiences who are no longer in the app, is easy to roll out, and can avoid distracting active users from completing core in-app goals; he cites seeing 20–40% response rates for research campaigns.

Better outreach starts simple and personal—don’t recreate a survey in one email.

Greg recommends plain-text outreach with simple, direct, highly relevant questions, avoiding stuffing too many questions into one message; he says a slower back-and-forth lets customers lead toward what they care about while still reaching many questions over time.

Map outreach to key journey drop-offs, not just post-churn.

Greg outlines multiple lifecycle touchpoints: people who start signup but don’t finish, check-ins during trial, and trial non-converters (where he says incentives for sharing insights can raise reply rates); he also calls out other abandonment moments like exploring an upsell feature but not converting, decreased usage, and canceled subscriptions.

WORDS WORTH SAVING

5 quotes

So back when I was a CPO at Bolt, I would've been, you know, happy to talk to seven or eight customers a month. And now with AI, you have the opportunity to 1,000X or even more how many customers you're able to engage with on a regular basis.

— Greg Greiner

In the modern world, you should be using AI to create a scaled representation of yourself to talk to your customers for you. It should also come back with what it's learned and share insights with you on a regular basis.

— Greg Greiner

I think it's now possible to actually have real back-and-forth conversations with thousands or even hundreds of thousands of customers every month in a way that would previously require an army of researchers, an army of support reps.

— Greg Greiner

We get, especially with these research campaigns, you know, 20, 30, 40% of these people responding.

— Greg Greiner

I think one of the things that AI enables is that, um, you can actually go back to that, you know, Uber-style ratio and have a PM and three or four engineers, but still, you know, create the output of that 25-engineer team.

— Greg Greiner

Read the available transcript
Scaled customer conversationsDrop-off funnel insights and conversion linkageEmail outreach vs in-app chatClaude Code agent setup (data source, instructions, triggers)Reply-rate drivers and rapid responseLifecycle touchpoints and incentivesEvals, groundedness, guardrails, and QA for customer-facing AI

Ask ChatGPT about this episode

Get its key ideas, plus a summary of each chapter linked to that point in the video, right in your chat.

  1. Add uListen AI to ChatGPT.

  2. Paste this prompt into a new chat.

    Use uListen AI to give me this episode's key ideas and a chapter-by-chapter summary, with timestamps: https://www.youtube.com/watch?v=JpyhPePe150

SPEAKERS

  • Greg Greiner

    guest

    Former CPO at Bolt and product leader (including Uber for Business), now CEO building AI-agent workflows for customer research.

  • Aakash Gupta

    host

    Host of Product Growth with Aakash Gupta; product/growth leader and newsletter author focused on AI and product management.

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

Get more out of YouTube videos.

Read along on your phone, search it beside the video, or ask your favorite AI app what was said.