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

The Right Model for Each Coding Task

Weave (YC W25) helps engineering teams understand whether their AI coding tools are actually making them more productive. Its models measure the work humans and agents produce and compare that output with AI spending. The company recently raised a $13.5M Series A led by Standard Capital and launched Weave Router, which selects models for different coding tasks. In this Fireside, co-founders Adam Cohen and Andrew Churchill discuss how they went from measuring human productivity to optimizing coding agents, why cost per output matters more than raw token spend, and how their AI coach helps engineers work more effectively with agents. They also share their vision for autonomous software factories and explain why combining different models’ strengths could outperform any single model. https://weaveos.com Chapters: 00:00 — Optimizing AI Coding With Weave 04:02 — Getting More From Your AI Budget 08:39 — Measuring Work Beyond Lines of Code 12:30 — From AI Adoption to Optimization 16:47 — Measuring AI ROI and Coaching Engineers 20:16 — Building Software Factories 25:38 — The Future of Model Routing Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs

Adam CohenguestAndrew Churchillguest

Nov 4, 202628mWatch on YouTube ↗

Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.

EPISODE INFO

Released: November 4, 2026
Duration: 28m
Channel: YC Root Access
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

Weave (YC W25) helps engineering teams understand whether their AI coding tools are actually making them more productive. Its models measure the work humans and agents produce and compare that output with AI spending. The company recently raised a $13.5M Series A led by Standard Capital and launched Weave Router, which selects models for different coding tasks. In this Fireside, co-founders Adam Cohen and Andrew Churchill discuss how they went from measuring human productivity to optimizing coding agents, why cost per output matters more than raw token spend, and how their AI coach helps engineers work more effectively with agents. They also share their vision for autonomous software factories and explain why combining different models’ strengths could outperform any single model. https://weaveos.com Chapters: 00:00 — Optimizing AI Coding With Weave 04:02 — Getting More From Your AI Budget 08:39 — Measuring Work Beyond Lines of Code 12:30 — From AI Adoption to Optimization 16:47 — Measuring AI ROI and Coaching Engineers 20:16 — Building Software Factories 25:38 — The Future of Model Routing Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs

SPEAKERS

Adam Cohen
guest
Co-founder of Weave; discusses engineering productivity metrics, agent evaluation, and model-routing economics.
Andrew Churchill
guest
Co-founder of Weave; focuses on the Weave Router’s technical approach to routing coding tasks across LLMs and evaluating outcomes.

EPISODE SUMMARY

In this episode of YC Root Access, featuring Adam Cohen and Andrew Churchill, The Right Model for Each Coding Task explores weave Router automates model choice to optimize AI coding cost Weave is described as a system that measures engineering productivity and quality, then uses those measurements to optimize how humans and coding agents deliver software.

RELATED EPISODES