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 79 episodes →-
EP 78 · AI Agents
What Breaks When Agents Become the Customer | Svix CEO Tom Hacohen
Tom Hacohen, Svix
-
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
By the numbers
- Episodes
- 79
- Downloads + full-episode views
- 167,054+
- YouTube subscribers
- 3,060
- Newsletter subscribers
- 1,200+
- Host following (LinkedIn + X)
- 17K+
As of October 24, 2026.
AI, decoded
Plain answers to the questions builders ask, each linked to the guests who have run into it.
- 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?
- MCP (Model Context Protocol) Should you use MCP or build a custom integration to connect AI to your tools?
- MCP (Model Context Protocol) How does MCP (Model Context Protocol) work?
- AI Coding Is AI taking software engineering jobs?
Browse by topic
- AI Agents
- AI Evaluation & Reliability
- Enterprise AI
- Open Source AI
- RAG & Retrieval
- AI Hardware
- AI Coding
- AI Observability
- Agent Memory
- AI Infrastructure
- Multimodal AI
- MCP (Model Context Protocol)
- Context Management
- 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.