Trace and debug eve agent sessions with Vercel Observability
Vercel Observability now provides visibility into eve agent framework sessions, showing trigger, duration, and token usage. Drill into individual runs to inspect model calls, tool calls, and runtime errors with Developer and Business mode views; retention scales from 12 hours to 3 days based on plan.
You can now view in your Vercel dashboard for , the open-source agent framework. The Agent Runs tab appears automatically for every eve project, surfacing trigger, duration, and token usage for each session at a glance. Drill into any run to inspect every turn, model call, and tool call in the conversation. Runtime errors that previously vanished into function logs now correlate to the failing step.Agent Runseve
Two views read the same data:
Run data is encrypted by default. Retention scales with plan:
Pro and Enterprise teams can extend retention to 30 days with .Observability Plus
Teams using a custom OpenTelemetry backend can still export AI SDK spans from to any destination, such as Braintrust or Datadog.agent/instrumentation.ts
Open in your project and read the to get started.Agent Runsdocumentation
shows raw tool names, input and output JSON, and per-step token counts for engineers debugging a failure.Developer mode
humanizes tool names, hides JSON, and generates a plain-English summary so a non-technical reviewer can audit what an agent did.Business mode
: 12 hoursHobby
: 1 dayPro
: 3 daysEnterprise
Source: original entry ↗