Archives

Making agents more effective isn't about chasing the latest model. It's about systematizing the feedback you're already giving and turning session learnings into persistent context.

A new computing paradigm is emerging where the agent is the runtime, natural language is the interface, and skills are starting to look a lot like apps.

Where software value moves when agents eat the rest.

Without evals, you're mostly guessing whether your AI product is working. Here's how to build a monitoring system that actually tells you.

Early pain points, rapid progress, and why CLI tools don't make MCP obsolete.