Skip to main content
The Understand section includes two inventories: Users (who is using your agent and how it is going for them) and Tool Catalog (every tool the agent calls and how reliably each one works). Both are built entirely from ingested conversations — there is nothing to configure.

​
Users

Open Understand → Users. Users are keyed by the user ID you attach to ingested events, so the page fills in once conversations arrive with user IDs set (see Ingestion overview). User aggregates refresh hourly.

​
User list

  • KPIs: Total Users, Active 7d, At Risk, Avg Health, plus charts for active users over time and the health-score distribution.
  • Cohort pills filter the list: power users, heavy tool users, frustrated, at risk, new this week, and silent sufferers. Clicking an active cohort clears it.
  • Search matches user IDs; wrap a term in double quotes ("user_123") for an exact match.
  • Time window presets: Last 24h, 7d, 30d, 90d.
  • Table columns: User, Convs, Health, Score, Top Intent, Signal, Last Seen. Page sizes 10/25/50/100 with numbered pagination.

​
Per-user history

Click a user to open their detail page (fixed 30-day window):
  • Header with identity and health status, and a stats row: Conversations, Turns, Tool Failures.
  • Callouts — notable findings for this user, such as failure signals, behavior concentration, and frustration trajectory.
  • Intent distribution and Frustration trajectory charts.
  • A Tool failures panel scoped to this user.
  • An Activity feed of the user’s conversations with a load-more control; each row opens the full conversation.

​
User memory

Moda also maintains a per-conversation user memory: a persona document extracted from the user’s messages (voice, decision style, constraints), updated within minutes as messages arrive. It appears on the conversation detail page in the World State view, under the collapsible “User memory” panel, with the number of messages seen and per-trait occurrence counts. The same document drives the user simulation in replays.

​
Tool Catalog

Open Understand → Tool Catalog (the page heading reads “Tool Catalogue”). Every tool call in ingested conversations produces a record within seconds, so the catalog is close to real time.

​
Tool inventory

  • KPIs: Total Calls, Unique Tools, Success Rate, Conversations.
  • Search by tool name, filter by effect, and pick a time range from Last 24 hours to Last 90 days.
  • Sortable columns: Tool Name, Calls, Success, Conversations, Effect, System, Last Seen.

​
Effect classification

Each tool is classified by the kind of effect it has: Tools whose effect cannot be determined show ?.

​
Tool detail

Clicking a tool opens a slideout with:
  • Overview — total calls, conversations, and failures for the selected period.
  • Input parameters — registered parameters merged with parameters observed in real calls, with types, call percentages, and common values.
  • Common uses — what the agent uses the tool for.
  • Usage over time — a call-volume chart.
  • Recent activity — recent calls with “View conversation” links.

​
Failure stats

The catalog shows the per-tool success rate and failure counts. For failure categories — what kind of error, the likely cause, and a suggested action — use Signals → Tool Failures, or the Data API’s GET /tool-failures and GET /tool-failures/:toolName.

​
Next steps

  • Signals — tool-failure categories, emotion, laziness, and hallucination detections.
  • Conversations — the World State view where per-conversation user memory appears.
  • Ingestion overview — how to attach user IDs so the Users page populates.