Step-by-step workflow for adding a new sub-agent or tool to the Pulse AI system. Use when creating a new ADK agent, tool, or extending the AI pipeline in pulse_ai/.
Cross-cutting workflow for adding a new alert metric spanning DB, backend, cron, frontend, and AI agent. Only invoke explicitly when adding a new metric type.
Step-by-step workflow for adding a new REST API endpoint to pulse-server. Use when creating a new backend endpoint, route, resource, or API in backend/server/.
Step-by-step workflow for adding a new reusable component to pulse-ui. Use when creating a shared component in pulse-ui/src/components/ (not a full screen/page).
Step-by-step workflow for adding a new screen/page to pulse-ui. Use when creating a new UI screen, page, dashboard view, or route in pulse-ui/.
Workflow for ClickHouse schema changes — adding columns, tables, or modifying the OTEL analytics schema. Use when making changes to ClickHouse tables in the otel database.
Workflow for building and deploying Pulse services locally via Docker. Use when building Docker images, starting/stopping services, or managing the local development environment.
Fatal Five — triages large-scale production failures by grounding hypotheses in repository code, ranking the top five failure modes by likelihood (P×I×E) with evidence and disconfirmers. Use when production is degraded at scale, SEV/incident response, post-incident review, outage, spike, or widespread regression; also when the user says Fatal Five or fatal-five.