aldersondev

Not-so-hot take: you need to measure your agent's performance in production.

Maybe-a-little-hotter-take: you should be using production data for evaluation rather than synthetic events.

Enter Online and offline evals; one measures performance in real time. The other, off the execution path, either before deployment, or after the agent run has happened. When to use both is explained in our latest guide!

`Exclude` has saved me more times than I can count, good to see it's not just me that reaches for it when fixing type bugs!

Codex 5.3 vs Claude Opus 4.6, who builds the better full-stack app?

I had both models build the exact same Next.js + TypeScript project,

An AI Job Application Analyzer that scores resumes against a job description and returns: match score (0–100) matched + missing skills tailored resume bullet rewrites interview questions

Langsmith just released their new AI powered agent builder platform. It allows you to write a prompt and build an AI automation out of it.

N8N, which is a very mature automation platform, also has a similar feature where you can type in a prompt to build an automation.

Lets build the same agent in both platforms using only an AI prompt see which tool works better.