Activity & observability

Every workflow run is recorded with a full trace of actions taken, model decisions, failures, and timing.

Every time a workflow runs, Terse records what happened: which trigger fired, what the model decided, which tools were called, whether it succeeded or failed, and how long it took. This data powers the Activity tab, the Stats dashboard, notifications, and the weekly self-improvement reviews.

You don’t need to add logging to your code. Observability is built into the platform.

Run lifecycle

Each run moves through a defined set of statuses:

Status	Meaning
In progress	The handler is currently executing
Success	The run completed without errors
Failed	The run threw an error or a tool call failed
Skipped	The filter function returned false. No handler executed, no tokens spent
Awaiting approval	A tool requiring human approval paused the run
Cancelled	The run was manually stopped

What gets recorded

Every run produces a run record with three layers of detail:

Run summary

The top-level record captures the basics: status, trigger source, trigger title, the model’s decision (processed or skipped), decision reasoning, whether it was manually triggered, and timestamps. This is what you see in the Activity list.

Action trace

Terse logs each side effect (a CRM record updated, a Slack message sent, a query executed) as an action with:

• The integration and tool name
• Whether it was a read or write
• A human-readable summary
• An optional link to the result (e.g., a URL to the created record)

Terse categorizes actions by type: create, update, delete, read, approve, or error.

Raw event stream

Terse stores the full model conversation as a sequence of raw events: every prompt, tool call, tool result, and model response, in order. That stream powers the run replay in the Activity drawer. You can step through the entire execution and see exactly what the model was thinking and doing at each point.

Activity tab

The Activity tab shows all runs across your workflows in one place, with the most recent runs first.

Search across run IDs, trigger titles, event content, decision reasons, and workflow names.

Filter by status to focus on failures, in-progress runs, or runs awaiting approval. Skipped runs are hidden by default to reduce noise. Toggle them on when you need them.

Filter by date range to narrow down to a specific time window.

Inspect a run by clicking any row. This opens a drawer with the full run replay: the trigger payload, the model conversation, tool calls with their arguments and results, and the final output. For runs awaiting approval, you can approve or reject directly from here.

From the run list, you can re-trigger the workflow with the same trigger payload, creating a new run on Terse. The run drawer surfaces a ready-to-copy terse replay command to replay the same payload against your local code instead. To list past runs and their payloads from the terminal, use terse history.

Stats dashboard

The Stats page aggregates run data into a dashboard with configurable time intervals (1 hour to 1 year):

Metric	What it shows
Events processed	Total runs (excluding skipped), with change vs. prior period
Actions taken	Total write actions across all runs
Active agents	Count of currently active workflows in your organization
Event volume over time	Run count over time, bucketed by the selected interval
Most active agents	Top 10 workflows by run count
Run status breakdown	Distribution across success, failed, cancelled, etc.
Trigger sources	Which integrations are firing the most triggers
Action integrations	Which integrations receive the most writes

Notifications

Terse can notify you about run outcomes through multiple channels:

Channel	What it supports
Slack	Action notifications, approval requests (interactive approve/reject buttons)
Email	Action notifications, approval requests, weekly improvement reviews
In-app	Pending approvals, sent notification history

You configure notifications per-workflow. Choose which action types to notify on (creates, updates, deletes, reads, errors, and approval requests) and Terse delivers to your preferred channel. Terse uses Slack when you have an active Slack destination configured; otherwise it falls back to email.

Terse records every notification it sends in your notification history, so you have an audit trail of what went out and when.

How observability feeds self-improvement

The same run data that powers Activity and Stats is also what the self-improvement system uses. The weekly review pulls run summaries, failed run traces, and action logs to identify patterns and recommend changes. Better observability means better improvement suggestions.

Where to go next

Human-in-the-loop

Require approval before specific tools execute.

Self-improvement

How Terse reviews past runs and recommends changes.