The dashboarding layer for metrics, logs, and traces.
The dashboarding layer that sits on top of Prometheus, Loki, and dozens of other data sources. We use Grafana to build the live dashboards students show off on Demo Day — request rate, p95 latency, agent loop depth, cost per request, all of it.
Top row: requests per second, p95 latency, error rate, $ per request. Middle row: token usage by model, agent loop depth distribution, tool-call success rate. Bottom: trace explorer for one-off debugging. The bootcamp ships a starter dashboard students customise.
Updates from the AI world — what shipped, what we’re using in production, and what’s worth your attention. Two emails a month, no spam.
