Part 3 of **Shipping AI Agents to Production. Part 1 covered eval gates and smoke evals. Part 2...
Our eval gate passed at 97%. The agent had written its own answers
Related
Composio vs Nango vs Scalekit: What Changes When Your Agent Goes to Production
The demo passed. The security review didn't. Here's a story you've probably lived, or will...
Decision models: the AI that can't ramble, and why my prompt-and-parse code wants one
On October 1, Cloudflare released Clef and Amazon released Strands Decider 2B on the same day. Both...
The Five-Step AI Roadmap Everyone Shares — and What I Actually Run in Production
The five-step AI roadmap circulates on every feed. Here is the honest version: which steps I run in production, which one I skipped, and what each is for.