---
schema: 1
type: video
title: >-
  He Built an AI Audience Simulator. It’s the Future of Customer Research. - Ep.
  49 w/ Michael Taylor
description: >-
  Michael Taylor has perfected the art of getting AI to speak in tongues. He’s
  taught it to mimic the voices of your customers—so you can see how they would
  respond before you ship. Michael is the creator of Rally, a market research
  tool that lets you simulate an audience of AI personas. He built a simulator
  that lets us A/B test Every’s headlines on an audience that mimics the real
  Hacker News audience. It’s become a part of my writing workflow, and I love it
  because you test your assumptions quickly, cheaply, and without any of the
  risks of putting something out into the world. Besides Rally, Michael
  co-authored a book on prompt engineering for O’Reilly, and he writes a column
  for Every about managing AI tools like you would people. In a past life, he
  founded a growth marketing agency which he grew to 50 people and sold in 2020.
  One of the reasons I’m drawn to Michael’s work is because he has a tinkerer’s
  mindset. He’s always exploring the limits of what a new technology can do, and
  what he’s into today, everyone else will likely discover six months later. We
  spent an hour talking about using language models to judge your work, best
  practices for assessing an AI’s performance, and Michael’s flow inside Cursor.
  He also demos Rally live on the show, testing three different potential
  headlines for an Every article. If you found this episode interesting, please
  like, subscribe, comment, and share! Want even more? Sign up for Every to
  unlock our ultimate guide to prompting ChatGPT here:
  https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only
  for paying subscribers, but you can get it here for free. To hear more from
  Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X:
  https://twitter.com/danshipper Timestamps: 00:00:00 - Episode start 00:01:32 -
  Introduction 00:04:30 - AI can simulate human personalities with remarkable
  precision 00:08:15 - How Michael simulated a Hacker News audience 00:15:04 -
  Push AI to be a good judge of your work 00:19:00 - Best practices to run evals
  00:23:01 - How AI compresses years of learning into shorter feedback loops
  00:27:01 - Why prompt engineering is becoming increasingly important 00:43:29
  - Adopting a new technology is about risk appetite 00:45:50 - Michael demos
  Rally, his market research tool 00:53:33 - The AI tools Michael uses to ship
  new features Links to resources mentioned in the episode: Michael Taylor:
  @hammer_mt Join the waitlist for Rally, Michael’s synthetic market research
  tool: https://askrally.com/ The book Michael co-authored on prompt
  engineering:
  https://www.oreilly.com/library/view/prompt-engineering-for/9781098153427/ The
  column Michael writes for Every: https://every.to/also-true-for-humans
  Michael’s article on personas of thought:
  https://every.to/also-true-for-humans/how-i-made-ai-think-like-a-focus-group
  Michael’s article on building a Hacker News simulator:
  https://every.to/also-true-for-humans/i-created-a-hacker-news-simulator-to-reverse-engineer-what-goes-viral
canonical: 'https://liquidgold.cc/watch/eREPh47BZbE'
markdown: 'https://liquidgold.cc/watch/eREPh47BZbE.md'
llms: 'https://liquidgold.cc/watch/eREPh47BZbE/llms.txt'
parent: 'https://liquidgold.cc/channel/everyinc.md'
channel: everyinc
updated: '2026-10-24T01:09:55.432Z'
language: null
children: []
videoId: eREPh47BZbE
durationSeconds: 3906
publishedAt: '2025-02-26T15:44:13.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 0
    endSeconds: 10
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=0'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 10
    endSeconds: 103
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=10'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 113
    endSeconds: 276
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=113'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 287
    endSeconds: 496
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=287'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 287
    endSeconds: 496
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=287'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 508
    endSeconds: 588
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=508'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 598
    endSeconds: 723
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=598'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 735
    endSeconds: 822
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=735'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 735
    endSeconds: 822
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=735'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 833
    endSeconds: 911
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=833'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 922
    endSeconds: 1144
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=922'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 922
    endSeconds: 1144
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=922'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 922
    endSeconds: 1144
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=922'
    heldReason: rights
  - ordinal: 13
    text: null
    startSeconds: 1393
    endSeconds: 1627
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=1393'
    heldReason: rights
  - ordinal: 14
    text: null
    startSeconds: 1393
    endSeconds: 1627
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=1393'
    heldReason: rights
  - ordinal: 15
    text: null
    startSeconds: 1627
    endSeconds: 1638
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=1627'
    heldReason: rights
  - ordinal: 16
    text: null
    startSeconds: 1729
    endSeconds: 1816
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=1729'
    heldReason: rights
  - ordinal: 17
    text: null
    startSeconds: 1816
    endSeconds: 1827
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=1816'
    heldReason: rights
  - ordinal: 18
    text: null
    startSeconds: 1914
    endSeconds: 1925
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=1914'
    heldReason: rights
  - ordinal: 19
    text: null
    startSeconds: 1925
    endSeconds: 2005
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=1925'
    heldReason: rights
  - ordinal: 20
    text: null
    startSeconds: 2016
    endSeconds: 2125
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2016'
    heldReason: rights
  - ordinal: 21
    text: null
    startSeconds: 2227
    endSeconds: 2361
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2227'
    heldReason: rights
  - ordinal: 22
    text: null
    startSeconds: 2372
    endSeconds: 2452
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2372'
    heldReason: rights
  - ordinal: 23
    text: null
    startSeconds: 2452
    endSeconds: 2463
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2452'
    heldReason: rights
  - ordinal: 24
    text: null
    startSeconds: 2463
    endSeconds: 2573
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2463'
    heldReason: rights
  - ordinal: 25
    text: null
    startSeconds: 2584
    endSeconds: 2614
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2584'
    heldReason: rights
  - ordinal: 26
    text: null
    startSeconds: 2625
    endSeconds: 2758
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2625'
    heldReason: rights
  - ordinal: 27
    text: null
    startSeconds: 2769
    endSeconds: 2872
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2769'
    heldReason: rights
  - ordinal: 28
    text: null
    startSeconds: 2987
    endSeconds: 3109
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=2987'
    heldReason: rights
  - ordinal: 29
    text: null
    startSeconds: 3121
    endSeconds: 3220
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3121'
    heldReason: rights
  - ordinal: 30
    text: null
    startSeconds: 3121
    endSeconds: 3220
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3121'
    heldReason: rights
  - ordinal: 31
    text: null
    startSeconds: 3232
    endSeconds: 3313
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3232'
    heldReason: rights
  - ordinal: 32
    text: null
    startSeconds: 3313
    endSeconds: 3324
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3313'
    heldReason: rights
  - ordinal: 33
    text: null
    startSeconds: 3436
    endSeconds: 3543
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3436'
    heldReason: rights
  - ordinal: 34
    text: null
    startSeconds: 3553
    endSeconds: 3641
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3553'
    heldReason: rights
  - ordinal: 35
    text: null
    startSeconds: 3652
    endSeconds: 3742
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3652'
    heldReason: rights
  - ordinal: 36
    text: null
    startSeconds: 3753
    endSeconds: 3864
    watch: 'https://liquidgold.cc/watch/eREPh47BZbE?t=3753'
    heldReason: rights
---


# He Built an AI Audience Simulator. It’s the Future of Customer Research. - Ep. 49 w/ Michael Taylor

Michael Taylor has perfected the art of getting AI to speak in tongues. He’s taught it to mimic the voices of your customers—so you can see how they would respond before you ship. Michael is the creator of Rally, a market research tool that lets you simulate an audience of AI personas. He built a simulator that lets us A/B test Every’s headlines on an audience that mimics the real Hacker News audience. It’s become a part of my writing workflow, and I love it because you test your assumptions quickly, cheaply, and without any of the risks of putting something out into the world. Besides Rally, Michael co-authored a book on prompt engineering for O’Reilly, and he writes a column for Every about managing AI tools like you would people. In a past life, he founded a growth marketing agency which he grew to 50 people and sold in 2020. One of the reasons I’m drawn to Michael’s work is because he has a tinkerer’s mindset. He’s always exploring the limits of what a new technology can do, and what he’s into today, everyone else will likely discover six months later. We spent an hour talking about using language models to judge your work, best practices for assessing an AI’s performance, and Michael’s flow inside Cursor. He also demos Rally live on the show, testing three different potential headlines for an Every article. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:00:00 - Episode start 00:01:32 - Introduction 00:04:30 - AI can simulate human personalities with remarkable precision 00:08:15 - How Michael simulated a Hacker News audience 00:15:04 - Push AI to be a good judge of your work 00:19:00 - Best practices to run evals 00:23:01 - How AI compresses years of learning into shorter feedback loops 00:27:01 - Why prompt engineering is becoming increasingly important 00:43:29 - Adopting a new technology is about risk appetite 00:45:50 - Michael demos Rally, his market research tool 00:53:33 - The AI tools Michael uses to ship new features Links to resources mentioned in the episode: Michael Taylor: @hammer_mt Join the waitlist for Rally, Michael’s synthetic market research tool: https://askrally.com/ The book Michael co-authored on prompt engineering: https://www.oreilly.com/library/view/prompt-engineering-for/9781098153427/ The column Michael writes for Every: https://every.to/also-true-for-humans Michael’s article on personas of thought: https://every.to/also-true-for-humans/how-i-made-ai-think-like-a-focus-group Michael’s article on building a Hacker News simulator: https://every.to/also-true-for-humans/i-created-a-hacker-news-simulator-to-reverse-engineer-what-goes-viral

Canonical: https://liquidgold.cc/watch/eREPh47BZbE · Channel: [Every](https://liquidgold.cc/channel/everyinc.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.