Episode
From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731
- Published
- May 13, 2025
- Duration seconds
- 3685
- Processing state
failed
Actions
POST https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/from-prompts-to-policies-how-rl-builds-better-ai-agents-with-mahesh-sathiamoorthy-731/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/twiml-ai-podcast/from-prompts-to-policies-how-rl-builds-better-ai-agents-with-mahesh-sathiamoorthy-731.md
Read the agent-friendly Markdown representation of this episode resource.
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 to prompting, and how it can improve multi-step tool use capabilities. We also explore the limitations of supervised fine-tuning (SFT) for tool-augmented reasoning tasks, the reward-shaping strategies they’ve used, and Bespoke Labs’ open-source libraries like Curator. We also touch on the models MiniCheck for hallucination detection and MiniChart for chart-based QA. The complete show notes for this episode can be found at https://twimlai.com/go/731.