How Too Much Information Destroys Agent Performance

Most AI agents fail because you're using them wrong. Here’s what actually works in production.

In this episode, Simon Maple (linkedin.com/in/simonmaple) sits down with Itamar Friedman (linkedin.com/in/itamarf) (CEO of Qodo) and Robert Brennan (linkedin.com/in/robert-a-brennan) (CEO of OpenHands) at QCon AI. They pull back the curtain on why agents hallucinate, provide inconsistent answers, and ship low-quality code.

On the docket:
• Why a third of developer-reported AI output is incorrect
• Why you must separate creative coding agents from structured review agents
• How excessive information destroys agent performance
• Parallelizing agents across 1,000+ repositories to resolve CVEs and legacy debt

Recorded live at QCon, this one's straight from architects building the future of the AI-native dev cycle.

Connect with us here:
Itamar Friedman: linkedin.com/in/itamarf
Robert Brennan: linkedin.com/in/robert-a-brennan
Simon Maple: linkedin.com/in/simonmaple
Tessl: linkedin.com/company/tesslio
AI Native Dev: linkedin.com/showcase/ai-native-dev

Check out the Qcon Batch one: youtu.be/OnM7sWLnAfw?si=mxtM_jdQJ_EdpLXt