Lean Agents: Decide What Your Agent Can Reach Before It Runs

As the Machine Learning Engineering Manager at an AI-powered SaaS company, I get a front-row seat to...

"Task completed successfully." That's the most common lie in agent systems. Usually the agent isn't...

I’ve been a backend dev for about four years, and lately, I feel like I'm attending the funeral of my...

I work on proxy infrastructure, which means I read a lot of proxy errors. And I kept noticing the...

Coding agents write their own session transcripts to disk. Where Claude Code, Codex and OpenCode keep those files, and how to find the session that belongs to your task.

I have three daughters. The oldest is four, the twins are two. None of them can read yet, and every...

There was a point while building Security Lens when I realized I was fixing problems faster than I...

TL;DR A partnership for security: Our new Sandbox Mixin Kit pairs Docker's isolated...

How to deploy a private, local AI gateway for engineering teams using LiteLLM, Caddy, Langfuse, and Open WebUI with multi-tier quotas.

For the Sanity Challenge, I decided to tackle Path One: Ship an agent that queries real content. As...