Skip to content

Stop building AI wrappers. Start building agent harnesses.

October 28, 2026 · 49 min

Show notes

I sit down with Jon Noronha, co-founder and chief product officer of Gamma, to break down agent harnesses and the startup openings around them. Jon explains how Gamma rebuilt its product as a creative agent this year and walks me through the roughly 20 models and 200 calls behind one finished presentation. We talk about AI smell, why taste carries more weight than evals in creative work, how Gamma tests a new model within the hour, and the fast mode test that lost to good friction. Jon also shares the harnesses he wants to see, from a Slack agent that learns his voice to a couch shopping tool that checks the fit in your room. If you want to build a vertical agent, this episode gives you a clear model of what a harness is and where your edge can come from.

This episode was made possible thanks to Anthropic (the team behind Claude) for hosting us at Claude Founder house and sponsoring the episode.

Timestamps

00:00 – Intro

01:23 – What Is an Agent Harness

03:36 – Harnesses as the New Wrappers

04:25 – Inside One Gamma Prompt

08:23 – Where Vertical Harnesses Fit

11:08 – Finding Your Edge

11:56 – Opportunities for Harnesses

13:09 – Designing a Niche Harness

13:48 – AI Smell

15:49 – Evals and Taste

18:40 – Who Pays for AI

19:44 – The Gamma for X

20:19 – A Harness for Slack

22:01 – Building on Other People's Models

23:28 – Closed vs. Open Source Models

24:11 – A Broad but Shallow Stack

24:57 – Prompts vs. Fine-Tuning

25:30 – Testing New Models

26:25 – Running Experiments

29:10 – The Marketing Engineer

32:26 – Interesting Automations

33:33 – The Top 1% Marketing Engineer

35:00 – Everyone Is Now a VP of Agents

36:19 – Experiments as a Numbers Game

38:26 – Underhyped: AI Image Models

40:42 – Startup Opportunities

45:40 – What Jon Would Build Next

47:26 – Closing Thoughts

Key Points

  • An agent harness is the set of tools an agent uses to act, check its own work, and deliver a finished result.
  • One Gamma presentation uses about 20 models and 200 calls, including rounds of visual QA.
  • Strong harness ideas sit in subjective work, where people care about the output and want a human in the loop.
  • Your edge comes from a distinct vision, proprietary data, or a business that mixes AI with the physical world.
  • Gamma gets 98% of its value from prompts and treats fine-tuning as a cost and quality optimization.
  • Experiments reward volume, and Gamma's fast mode test showed that good friction raised paid conversion.

FIND ME ON SOCIAL

X/Twitter: https://twitter.com/gregisenberg

Instagram: https://instagram.com/gregisenberg/

LinkedIn: https://www.linkedin.com/in/gisenberg/

FIND JON ON SOCIAL

X/Twitter: https://x.com/thatsjonsense?lang=en

LinkedIn: https://www.linkedin.com/in/jonnoronha/

All episodes of The Startup Ideas Podcast

Settings

Display

Language

Decides which stations you see first on the home page.

History

Recently played stations and episodes and your latest searches are only stored in this browser.

Notifications

A short notice when a podcast you follow has a new episode. Turn off single podcasts with the bell on their page.

Account

Save favorites – in the app and on the website.

Keyboard shortcuts

/
Open search
Space
Play or pause
← →
In the player: back 15 s, forward 30 s (episodes) · in a row: next tile
↑ ↓
In a row: target within the tile
Home / End
In a row: first or last tile
Esc
Close window or menu
?
This overview
Now playing

Go to station page

Play next

    Add episodes with “Play next” – they play after the current episode.