Investigations
When a Reliability alert fires, Morse runs a first-pass investigation automatically — pulling in infra signals, a baseline comparison, recent deploy revisions detected from trace metadata, sample failed traces, and correlated alerts — and hands you back an AI-generated hypothesis, the model’s own confidence rating (high, medium, or low — a self-assessment, not a calibrated probability), and the evidence it looked at. It is a starting point for your own check, not a verified cause.
Trace references in the structured evidence are checked against your organization’s stored traces before an investigation is saved, so those links point to traces you can open.
This screen is the command center: a queue of every investigation, and a detail pane for the one you’ve selected.
What you see
The page renders a summary strip above a two-pane layout: a state-aware queue on the left, a detail preview on the right.
Summary strip
Five clickable tiles — All, Active, High confidence, Needs review, Failed — each showing a server-computed count.
Clicking a tile filters the queue below to that segment. The bucket itself is decided once on the backend — the same function backs both the per-row segment and this aggregate count, so the tile counts and the rows in the queue never disagree.
Investigation queue
Each row shows the agent name, an alert-type badge, a status or confidence badge, a one-line hypothesis, who investigated it (a specific model name, or “Morse AI” as a fallback), evidence count, recommended-action count, cost, and how long ago it ran.
A run that hasn’t landed a high-confidence hypothesis reads “Couldn’t form a confident hypothesis — needs review,” in italics, rather than showing a shaky guess as if it were settled.
Detail panel
Selecting a row opens its hypothesis, evidence grouped by kind (Traces, Metrics, Logs, Changes, Alerts, Evals), a numbered list of recommended actions, and a run-facts grid — status, model, cost against its cap, and duration.
An action rail lets you jump to the fired alert, the referenced trace(s), Copilot (with a pre-filled prompt about this investigation), the Reliability SLO config for burn-rate alerts, or Evals when eval evidence is present.
On narrower screens the detail panel opens in a bottom sheet instead of a side pane.
Cost and confidence
Each investigation runs against a per-run dollar cost cap — $0.05 by default, about a nickel, unless your organization or a specific alert overrides it.
A run that hits its cap stops rather than overspending, and still saves whatever partial result it had — it doesn’t fail silently.
How to use it
- Click a summary tile to filter the queue to that state.
- Click a row to load its hypothesis, evidence, and recommended actions in the detail pane.
- From the detail pane, jump to the alert, the trace(s) referenced as evidence, Copilot, Reliability, or Evals.
- Arriving from a fired alert with
?alert_id=in the URL preselects that alert’s investigation in the detail pane automatically.
Before you have data
Until an alert fires, the queue is honest about being empty:
- No investigations yet: “No investigations yet.”, with a short explainer of how investigations work and links to configure an alert or inspect recent alerts.
- A filtered segment with no matches: “No investigations match this filter.”
If the request to fetch investigations fails outright, the queue shows a “Couldn’t load investigations” state with a Retry button.