Agents
What everyone was talking about at WeAreDevelopers World Congress North America
After 237 talks across eight stages, code review emerged as the bottleneck for AI-generated code. Here are the production eval, sandbox, context, and agent experience themes that kept showing up. The
After 237 talks across eight stages, code review emerged as the bottleneck for AI-generated code. Here are the production eval, sandbox, context, and agent experience themes that kept showing up. The post What everyone was talking about at WeAreDevelopers World Congress North America appeared first on Arize AI.
Related
- The best eval harness for production AI and agents: A comparison
- Code mode: Why your agent should code
- Inside Cursor’s agent factory: how it verifies AI-written code
- Building smarter AI agents: architecture, evals, and lessons from the field
- Beyond models: How context and evals make agents work in production
Source: Arize AI | 2026-09-29