[HN Gopher] Show HN: 83 browser-use trajectories, visualized
       ___________________________________________________________________
        
       Show HN: 83 browser-use trajectories, visualized
        
       Hey all, Justin here. I previously built Phind, the AI search
       engine for developers.  One of the biggest problems we had there
       was figuring out what went wrong with bad searches. We had tons of
       searches per day, but less than 1% of users gave any explicit
       feedback. So we were either manually digging through searches or
       making general system improvements and hoping they helped.  This
       problem gets harder with agents. Traces are longer and more
       complex. It takes more effort to review them, so I'm building a
       tool that lets you analyze LLM outputs directly to help developers
       of LLM apps and agents understand where things are breaking and
       why.  I've put together a demo using browser-use agent traces
       (gpt-5): https://trails-red.vercel.app/viewer  It's early, but I
       have lots of ideas - live querying of past failures for currently-
       running agents, preference models to expand sparse signal data.
       Would love feedback on the demo. Also if you're building agents and
       have 10k+ traces per day that you're not looking at but would like
       to, I'd love to talk.
        
       Author : wayy
       Score  : 6 points
       Date   : 2026-01-23 19:50 UTC (3 hours ago)
        
 (HTM) web link (trails-red.vercel.app)
 (TXT) w3m dump (trails-red.vercel.app)
        
       ___________________________________________________________________
       (page generated 2026-01-23 23:01 UTC)