{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Chain of Thought | AI Agents, Infrastructure & Engineering","title":"Architecting AI Agents: The Shift from Models to Systems | Aishwarya Srinivasan","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/a22109d3\"></iframe>","width":"100%","height":180,"duration":3206,"description":"Most AI agents are built backwards, starting with models instead of system architecture.\nAishwarya Srinivasan, Head of AI Developer Relations at Fireworks AI, joins host Conor Bronsdon to explain the shift required to build reliable agents: stop treating them as model problems and start architecting them as complete software systems. Benchmarks alone won't save you. \nAish breaks down the evolution from prompt engineering to context engineering, revealing how production agents demand careful orchestration of multiple models, memory systems, and tool calls. She shares battle-tested insights on evaluation-driven development, the rise of open source models like DeepSeek v3, and practical strategies for managing autonomy with human-in-the-loop systems. The conversation addresses critical production challenges, ranging from LLM-as-judge techniques to navigating compliance in regulated environments.\nConnect with Aishwarya Srinivasan:\nLinkedIn: https://www.linkedin.com/in/aishwarya-srinivasan/\nInstagram: https://www.instagram.com/the.datascience.gal/\nConnect with Chain of Thought host Conor Bronsdon: https://www.linkedin.com/in/conorbronsdon/\n00:00 Intro — Welcome to Chain of Thought\n00:22 Guest Intro — Ash Srinivasan of Fireworks AI\n02:37 The Challenge of Responsible AI\n05:44 The Hidden Risks of Reward Hacking\n07:22 From Prompt to Context Engineering\n10:14 Data Quality and Human Feedback\n14:43 Quantifying Trust and Observability\n20:27 Evaluation-Driven Development\n30:10 Open Source Models vs. Proprietary Systems\n34:56 Gaps in the Open-Source AI Stack\n38:45 When to Use Different Models\n45:36 Governance and Compliance in AI Systems\n50:11 The Future of AI Builders\n56:00 Closing Thoughts & Follow Ash Online","thumbnail_url":"https://img.transistorcdn.com/Qn8RSZeOW_fLo0VHUhIAyNP8D0ABIIQ39lKvvuHniR8/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS85ZWU3/Mjk4NDcwNGRiOGI4/NWUwMTQ0ZjA1NjM3/ZWU0Ny5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}