Proactive Agents for the Web with Devi Parikh - #756
From The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) by Sam Charrington
November 19, 2025 · 56 min · Episode 756
About this episode
Devi Parikh discusses the future of web interaction through proactive, autonomous agents and the technical challenges involved.
Today, we're joined by Devi Parikh, co-founder and co-CEO of Yutori, to discuss browser use models and a future where we interact with the web through proactive, autonomous agents. We explore the technical challenges of creating reliable web agents, the advantages of visually-grounded models that operate on screenshots rather than the browser’s more brittle document object model, or DOM, and why this counterintuitive choice has proven far more robust and generalizable for handling complex web interfaces. Devi also shares insights into Yutori’s training pipeline, which has evolved from supervised fine-tuning to include rejection sampling and reinforcement learning. Finally, we discuss how Yutori’s “Scouts” agents orchestrate multiple tools and sub-agents to handle complex queries, the importance of background, "ambient" operation for these systems, and what the path looks like from simple monitoring to full task automation on the web. The complete show notes for this episode can be found at https://twimlai.com/go/756.
People in this episode
Host: Sam Charrington
Guest: Devi Parikh
Topics covered
- proactive agents
- web interaction
- autonomous systems
- technical challenges
- training pipeline
- task automation
Keywords
- proactive agents
- browser use models
- reliable web agents
- visually-grounded models
- training pipeline
- task automation
Mentioned in this episode
Organizations: Yutori
More episodes of The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
- Is RAG Dead? Lessons from Building AI for Tax Law with Alex Bowcut - #769 · June 9, 2026 · 52 min
- Relational Foundation Models for Enterprise Data with Jure Leskovec - #768 · May 21, 2026 · 1h 6m
- How to Find the Agent Failures Your Evals Miss with Scott Clark - #767 · May 7, 2026 · 53 min
- How to Engineer AI Inference Systems with Philip Kiely - #766 · April 30, 2026 · 55 min
- How Capital One Delivers Multi-Agent Systems with Rashmi Shetty - #765 · April 16, 2026 · 54 min
- The Race to Production-Grade Diffusion LLMs with Stefano Ermon - #764 · March 26, 2026 · 1h 3m
Explore listener stats, chart rankings, contacts and more on the The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) podcast page.