How Agent Observability took Pencil from Black Box to Control Center
See how agent observability with Netra helped Pencil trace failures, speed root-cause analysis, and gain control over multi-step agent workflows.
AI Agents
Beyond Single Turns: What We Learned Running Multi-Agent Simulation at Scale
Multi-turn conversation testing shows where agents drift, forget context, or miss goals. Discover what single-turn evals miss.
Why You Can't Unit Test Your Way to Reliable Agents
We build AI agents. We've shipped twenty five of them — travel, customer service, scheduling, voice transcription. Every single one broke in production despite having tests....
What We Learned Shipping 9 AI Products
Last March, our travel AI sent a user to a resort that doesn't exist. They'd asked for a road trip itinerary. The AI confidently included "Sunoutdoors Resort" as...