Activity & evidence

See what an agent did through Alvoki.

Useful agent work should leave enough evidence to review the caller, tool call, approval, provider result, transcript, and output.

Recent activity

See what ran, what failed, and what paused for approval.

Recent activity showing successful, failed, and approval-paused GitHub calls from the Maintenance agent
The identity view shows a small operational history: what succeeded, what failed, and which sensitive action paused for approval.

Call

The Agent identity, tool, grant, status, and timestamps.

Decision

The exact payload, approval outcome, and provider result.

Wider run

The related transcript, workflow run, and output when available.