Agent Runs

Agent Runs lets you inspect eve sessions, turns, tools, reasoning, timing, and token usage in the Edgenivo dashboard. It appears automatically for eve projects, with no instrumentation file required.

Agent Runs usage is billed at Always-on Tracing rates during beta. All plans include 30-day Agent Runs retention during beta.

Open your project in the Edgenivo dashboard and go to Agent Runs.

The overview shows:

• Runs over time, broken down by trigger, such as Slack and HTTP.
• Token usage over the same window, split into input, output, and cached tokens.
• A table of runs with the triggering message, trigger type, tokens in and out, turn count, duration, and time.

Select a run to see its model, trigger, and deployment, followed by a per-turn breakdown with:

• Timings for each step in the turn, including skill loads and individual tool calls.
• Input and Output for the turn.
• Reasoning the model produced along the way.
• Tool Calls made during the turn, with their arguments and results.
• Input, cached, and output token counts for the turn.

Agent Runs is eve's built-in OpenTelemetry integration for Edgenivo. Configure it with agentRuns(). New eve deployments automatically configure tracing to sample at 100%. Existing deployments must configure sampling.

To investigate an agent's actions, connect its tool calls with the initiating identity, approval records, and changes recorded by downstream systems. Agent Runs captures execution traces; your application and connected systems must supply the approval and outcome records. Read How do you audit what an AI agent did? for guidance on reconstructing a run and handling gaps in the evidence.

New eve deployments automatically configure tracing to sample at 100%. Existing deployments must add a tracing rule before Edgenivo collects traces. We recommend sampling at 100% to collect all of the spans related to the run.

For an existing deployment, select your team and project, then open Settings → Tracing:

1. Select Add Sampling Rule.
2. Choose All Environments, Production, or Preview.
3. Set Rate to 100%.
4. Select Save.

Tracing starts when you save the rule. You can also manage sampling rules with vercel traces config. The CLI accepts rates from 1% to 100%. Add a 0% rule from the dashboard.

If your agent processes personal, sensitive, or regulated data, you may need to disclose this capture under applicable laws and in your privacy materials.

The process-wide otel({ tracePolicy }) setting controls the maximum content available to every OpenTelemetry destination. Use recordInputs and recordOutputs to control content capture. Agent Runs cannot restore content excluded by this policy. See Configure process-wide trace content for an example.

Use agent/instrumentation/agent-runs.ts to further narrow what Agent Runs receives. For example, retain spans for private sessions while redacting their inputs and outputs:

import { agentRuns } from 'eve/instrumentation/otel';
 
export default agentRuns({
  exportPolicy: {
    span: ({ audience }) =>
      audience === 'public'
        ? { emit: true }
        : { redact: true, inputs: true, outputs: true },
  },
});

Input redaction removes eve's known prompt, instruction, document, and tool-argument attributes. Output redaction removes response, reasoning, tool-result, exception, and status attributes. Redaction affects only Agent Runs and does not mutate spans sent to another destination.

Use vercel agent-runs to inspect runs from your terminal or a coding agent with shell access:

vercel agent-runs projects --scope my-team
vercel agent-runs list --scope my-team --project my-app
vercel agent-runs inspect run_1234567890 --scope my-team --project my-app
vercel agent-runs trace run_1234567890 --scope my-team --project my-app

Replace the example team, project, and run ID with your own. Commands default to production; add --environment preview for preview runs. Every subcommand supports --json. The default trace view summarizes conversation turns as Markdown and truncates long content. Use --json --max-field-length 0 to read untruncated field values from a trace page. See the CLI reference for time filters, pagination, and output details.

Connect a supported client to Edgenivo MCP to investigate agent activity from your coding assistant. The Agent Runs tools let you find projects, select a run, and inspect its metadata and trace:

For example, ask your client: "Find recent Agent Runs for my project, then inspect the tool calls in the latest run." Specify the team, project, environment, and time window when you need to narrow the results.

Trace results can be paginated or unavailable. Follow the trace response and pagination guidance before treating an empty result as evidence that a run had no activity.

• Observability: configure process-wide OpenTelemetry settings and third-party destinations.
• Concepts: learn how eve's runtime pieces fit together.
• Edgenivo Observability: inspect traces alongside logs and metrics.