Chain of Thought Podcast
(opens in new tab) Conversations with the people building AI agents and infrastructure.
Hosted by Conor Bronsdon, for engineers, founders, and operators shipping AI. Guests from NVIDIA, Google DeepMind, AMD and more.
Guests from
More recent episodes
All 78 episodes →-
EP 77 · AI Agents
Switching Models Shouldn't Mean Starting Over | Walrus Protocol's Kimberly Logan
Kimberly Logan, Walrus Protocol
-
EP 76 · Enterprise AI
Your Best AI Engineer Might Have the Worst Metrics | Sonar CTO Andrea Malagodi
Andrea Malagodi, Sonar
-
EP 75 · AI Agents
Why Context Alone Isn't Enough for Enterprise AI Agents | WisdomAI CPO Kapil Chhabra
Kapil Chhabra, WisdomAI
By the numbers
- Episodes
- 78
- Downloads + full-episode views
- 166,259
- YouTube subscribers
- 3,050
- Newsletter subscribers
- 1,200+
- Host following (LinkedIn + X)
- 17K+
Downloads + views, YouTube, and episode count update live from the Chain of Thought dashboard.
AI, decoded
Plain answers to the questions builders ask, each linked to the guests who have dealt with it in production.
- Enterprise AI Why do most enterprise AI projects fail to show ROI?
- AI Evaluation & Reliability Should you evaluate AI with an LLM-as-a-judge or with human review?
- AI Evaluation & Reliability What's the difference between AI observability, evaluation, and benchmarking?
- AI Security How do you give an AI agent an identity and permissions?
- MCP (Model Context Protocol) Should you use MCP or build a custom integration to connect AI to your tools?
- Multi-Agent Systems Should you build a single agent or a multi-agent system?
Browse by topic
- AI Agents
- AI Evaluation & Reliability
- Enterprise AI
- Open Source AI
- RAG & Retrieval
- AI Hardware
- AI Coding
- AI Observability
- Agent Memory
- Multimodal AI
- MCP (Model Context Protocol)
- Context Management
- AI Infrastructure
- AI Energy & Data Centers
- AI Engineering
- AI Security
- Multi-Agent Systems
- Model Training
- Model Architecture
Sponsor the show
Reach the engineers and AI leaders who choose what gets built.