Coming soon
Why Agent Workflows Need Investigation, Not Just Monitoring
Traces show events. APMs show spans. Neither explains whether the workflow was correct, allowed, efficient, safe, or worth changing.
Blog
Thoughts on agent workflow investigation, AI observability, and building the neutral layer that explains what matters.
Coming soon
The Fabricated Citation Problem in Multi-Agent Systems
When agents cite evidence they never retrieved, traditional observability says "run completed." We think that's not enough.
Coming soon
Customer-Specific Priorities: Why Generic Dashboards Miss the Point
Harvey cares about correctness. Decagon cares about refund risk. Cursor cares about unsafe edits. One dashboard can't serve all three.