Best Chain of Thought Episodes on AI Security
Attacking agents, defending them, and the part software cannot cover.
Agent security isn’t application security with a model attached. The attacker gets a system that follows instructions faithfully, including the ones you didn’t write, and every tool you connect widens what a single bad instruction can reach. Four episodes here, because a fifth would have been padding.
- 1 You Can't Secure an AI Agent with Software Charles Guillemet, Ledger Ledger CTO Charles Guillemet argues you cannot secure an agent with software permissions and API keys once it is moving real money, and makes the case for a hardware-enforced signature between intent and execution.
- 2 The First Fully Autonomous AI Attack is Coming | Kristin Lovejoy Kristin Lovejoy, Kyndryl Kristin Lovejoy’s prediction: a fully autonomous attack that takes an enterprise network down with no human driving it, inside 18 months. Her reasoning runs through attackers chaining low-risk vulnerabilities, which changes the patching math.
- 3 We Built Agents, Nobody Built HR | Tyler Akidau, Redpanda Tyler Akidau, Redpanda Tyler Akidau on the four pillars of agent governance, and why guardrails written where the agent can see them are not guardrails. Task-scoped identity is the foundation the rest sits on.
- 4 Vercel's Playbook for AI Agents: From Vibe Check to Production | Malte Ubl Malte Ubl, Vercel Vercel’s Malte Ubl on the security lesson people get wrong most often: prompt injection is not SQL injection, and the answer is constraining what the tool can do rather than filtering what goes in.
- Best Chain of Thought Episodes for AI Founders Building an AI company — defensibility, GTM, and the market reality.
- Best Chain of Thought Episodes for Engineers Shipping with AI — the craft, the workflow, and the reality checks.
- Best Chain of Thought Episodes on AI Agents How agents actually work — architecture, memory, context, frameworks.
- Best Chain of Thought Episodes on AI Evaluation Measuring whether AI actually works — evals, reliability, trust.
- Best Chain of Thought Episodes on Agent Memory How agents remember — memory stores, context engineering, and what breaks without them.
- Best Chain of Thought Episodes on Multi-Agent Systems Many agents, one system — orchestration patterns, protocols, and the overhead they add.
- Best Chain of Thought Episodes on Open Source AI Open weights, open ecosystems, and what they actually cost in production.
- Best Chain of Thought Episodes on AI Coding Agents What changes downstream when agents write most of the code.
- Best Chain of Thought Episodes for Enterprise AI Leaders Getting AI past the pilot — ROI, rollout, and the data underneath it.
- Best Chain of Thought Episodes on RAG & Retrieval Getting the right context to the model: chunking, vectors, graphs, and what breaks at scale.