What problem does it solve?
On-call engineers need a quick, consolidated view of current operational health across many internal systems, but manually checking IcM incidents, ADO pipelines, Kusto error rates, Teams alerts, and WorkIQ action items is slow and fragmented.
Core Features & Use Cases
- Parallel Multi-Source Data Gathering: Launches six background agents simultaneously to query IcM incidents, ADO pipeline builds, the Loop-FF integration pipeline, Kusto session error rates, Teams pipeline alerts, and WorkIQ action items.
- Best-Effort Resilience: Uses a 90-second hard timeout so partial results are always presented, with failed or timed-out sections clearly marked as unavailable.
- Structured Dashboard Output: Renders a Markdown dashboard with tables for incidents, pipeline health, error rates, alerts, and follow-ups, optionally written to a timestamped file.
- Use Case: At the start of an OCE shift, ask for a shift status dashboard to immediately see active incidents, failing builds, elevated partner error rates, and unacknowledged pipeline alerts in one view.
Quick Start
Ask the assistant to generate a shift status dashboard and confirm when prompted, making sure you are connected to the VPN first.
