Your agents could be failing silently right now. Find out in 2 min →

Syrin Blog

Engineering notes on
autonomous AI

Clear thinking on agent observability, reliability, and what it actually takes to run AI in production.

I Gave My Coding Agent Eyes Three Different Ways. Here's the Honest Scorecard.
Featured
Benchmarks

I Gave My Coding Agent Eyes Three Different Ways. Here's the Honest Scorecard.

Playwright MCP, Chrome DevTools MCP, and Iris all let an AI coding agent see a running web app. I built Iris, so I ran a committed benchmark across all three and wrote down where each one wins and where mine loses.

Divyanshu Shekhar··17 min read
Read

More posts