...
connecting...
--uptime
--routers
--queue
--today
Action Center
Name Tier Schedule Status Last Run CLI Duration 7d Actions
Activity Feed
Upcoming
--
--|--|--|--
↗ Open in Obsidian
Schedule
--|--|
SKILL.md
Task Files
Select a file
Click a file in the tree to view its contents.
Configuration
T1
No
Run History
DateCLIStatusDuration
CLI Chain
Manual Feedback
Briefing Reactions
Pending Operator Requests
Recent Feedback Stream
Today's Debriefs
Meeting Info
Debrief Instructions

AI Providers

Connector Auth Status

Not checked yet — click Run Check
What this screen is

Experiments reads per-task run telemetry under ~/.agents/sentinel/experiments/<task>/ (runs, success rate, sparklines, optional synthesis.md). Use it to spot flaky or regressing scheduled tasks.

If another browser or Cursor’s preview is missing tabs like this one, compare the build stamp next to the freshness dot in the header, or open /api/meta on the same host and port.

Task Experiment History
Task Runs Success Rate Trend Last Run Sparkline (last 30) Synthesis Variants
Webhook & label
Runs
Issue Status Received Processed Writes Summary
--
Run record