Skip to main content

Posts

Featured

The Agent Stack Bet

Peek under the hood of most "production agents" shipping today and you won't find intelligence. You'll find custom plumbing, fragile session logic, shared service accounts, and a security model held together by hope. This can be so much better. If you've spent the last 18 months putting agents into production, you already know the models and tools have gotten dramatically better. You also know the problems still burning in your on-call rotation are not ones you can prompt your way out of. We are running into a stack ceiling, and it is quietly creating a governance and reliability gap that the next generation of agentic systems cannot grow through. Read More

Latest Posts

Load Balancing and Scaling LLM Serving

New undersea cable cutter risks Internet's backbone

Android CLI and skills: Build Android apps 3x faster using any agent

Stop comparing price per million tokens: the hidden LLM API costs

Let the commits tell the story

Verified Argo CD deployments

Cloudflare Client-Side Security: smarter detection, now open to everyone

North Korean hackers blamed for hijacking popular Axios open source project to spread malware

Inside the Claude Code source

The Developer's Playbook: Defending Gates and Scaling Systems