Stop building AI wrappers. Start building agent harnesses.

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/