Mahesh Sathiamoorthy
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy
- Published
- May 13, 2025
- Duration
- 1h 1m
- Summary source
- description
- Last updated
- Jul 5, 2026
Discusses agents, fine-tuning.
Summary
Today, we're joined by Mahesh Sathiamoorthy, co-founder and CEO of Bespoke Labs, to discuss how reinforcement learning (RL) is reshaping the way we build custom agents on top of foundation models. Mahesh highlights the crucial role of data curation, evaluation, and error analysis in model performance, and explains why RL offers a more robust alternative t…
Intelligent Report
Sign in to read teasers, or upgrade to Research Pro to commission intelligent report for this episode. Learn more →
Show notes
Today, we're joined by Mahesh Sathiamoorthy, co-founder and CEO of Bespoke Labs, to discuss how reinforcement learning (RL) is reshaping the way we build custom agents on top of foundation models. Mahesh highlights the crucial role of data curation, evaluation, and error analysis in model performance, and explains why RL offers a more robust alternative to prompting, and how it can improve multi-step tool use capabilities. We also explore the limitations of supervised fine-tuning (SFT) for tool-
Themes
- agents
- fine-tuning