AI Agents

Why AI Agents Get Infrastructure Wrong - And How Context Helps

The most dangerous infrastructure mistake isn't always a made-up resource. It is a confident answer built from half the truth. Ask an AI whether a service is exposed to the internet. It inspects the service, finds no security group directly atta…

You Can Only Break What You Know About

Chaos engineering has a premise I find genuinely convincing. Tests only check the cases you thought of. Injecting real failure into a real system finds the ones you did not. It also has a problem sitting right at the front of it, and I have not seen i…

Similar Code Is Not Connected Code

Ask an embedding-based system which code relates to PaymentService and you will get back things that look like PaymentService . Other payment classes. Functions with payment in the name. A test file. Possibly a payment integration in a completely dif…

The Feature Ends at a String Literal in Someone Else's Repository

Somebody asks how order creation works. You open the order service and start reading. POST /orders → OrderController.create() → OrderService.submit() → orders table → publish("order.created") And that's where the trail stops. Not bec…

Your AI Agent Does Not Need Write Access

In July 2025 a founder named Jason Lemkin was nine days into a twelve-day experiment with Replit's AI coding agent. A code freeze was in effect. The agent had been told, repeatedly, not to change anything. It ran destructive commands against the…

Your AI Agent Is Not Dumb. You Gave It Too Many Tools.

There is a number in the MCP research that should have changed more minds than it did. Researchers working on the RAG-MCP project measured what happens to an agent's ability to pick the right tool as the tool list grows, and as AgentPMT reported i…

Load More
That is All