Run history
Watch the tutorial
Run History provides comprehensive visibility into all AI Colleague executions across your organisation. It enables administrators, managers, and implementation teams to monitor performance, troubleshoot issues, and analyse business outcomes through a centralised dashboard.
Key Components:
- Executions Table: View and manage all AI Colleague runs in a sortable, filterable table
- Global Filters: Filter executions by time range, AI Colleague, AOP, status, and more
- Run Details: Drill down into individual executions for step-by-step analysis
- Export Capabilities: Export execution data for external analysis and compliance
Accessing Run History
-
Navigate to AI Colleagues from the main navigation
-
In the left sidebar, expand Insights
-
Click Run history: The default landing view displays the Executions Table with the most recent runs.
User Personas:
Role Access Level System Admins Full access to all AI Colleague executions and configurations
Executions Table
The Executions Table displays all AI Colleague runs in a comprehensive, sortable format. Each row represents a single execution with key metadata for quick assessment.
Default Table Columns
| Column | Description |
|---|---|
| Run ID | Unique identifier for the execution. Clickable to open drill-down view. |
| Handled by | AI Colleague(s) that handled the request/run. |
| Trigger Type | How the execution was initiated: Manual, System/Workbench, or API |
| Status | Current execution state with colour coding (see Status Definitions below) |
| Initiated By | User who triggered the execution (Manual), or "N/A" for Workbench/API triggers |
| Initiated For | User for whom the request was raised, or "N/A" |
| Initiated On | Timestamp when the request was initiated (sortable) |
| Completed On | Timestamp when finished, or "N/A" for in-progress executions |
| Total Time Taken | Duration in format: X Year(s) X Month(s) X Day(s) X Hour(s) |
| Input Tokens | Total input tokens consumed across all LLM calls in the run |
| Output Tokens | Total output tokens consumed across all LLM calls in the run |
Status Definitions
| Status | Description |
|---|---|
| Handled | Request completed successfully |
| Unhandled | Request failed during execution |
| In Progress | Execution currently running (includes waiting for user input) |
| Cancelled | Request cancelled by user or system |
Additional Available Columns
The following columns can be enabled via the Edit Columns option:
| Column | Description |
|---|---|
| Escalation | True/False - whether escalation to Escalation Manager occurred |
| Channel | Communication channel: Voice, Slack, Web, etc. |
| Associated AOPs | List of AOPs executed during the run |
| Associated Skills | List of Skills executed during the run |
| Schedule Name | Name of the schedule (for System/Workbench triggers) |
| Participation Coverage | Participants involved (clickable to view list) |
| Unhandled Due To | Category of failure (see Failure Categories) |
| Unhandled Reason | Detailed LLM-generated failure explanation |
Filtering & Search
Global Filters
Filters persist across your session and can be combined to narrow down results.
Time Range Filter
| Option | Description |
|---|---|
| Last 7 days | Executions from the past week |
| Last 30 days | Executions from the past month (default) |
| Last 90 days | Executions from the past quarter |
| Till Now | All executions since deployment |
| Custom | Specify custom start and end dates |
Handled By Filter
Multi-select dropdown to filter by specific AI Colleagues.
- No selection (default): Shows executions from all AI Colleagues
- Select AICs: Quick filter for all AI Colleagues (active/inactive)
AOP Filter
Multi-select dropdown to filter by Agent Operating Protocols.
- No selection (default): Shows all executions
- Select AOPs: Choose specific AOPs that handled one or more runs.
Skill Filter
Multi-select dropdown to filter by Skills.
- No selection (default): Shows all executions
- Select skills: Choose specific skills that handled one or more runs.
Status Filter
Multi-select selection (Select one or more for status specific drill-down):
- No selection (default): All executions
- Handled: Only handled runs
- Unhandled: Only unhandled runs
- In progress: Only in progress runs
- Cancelled: Only cancelled runs
Escalation Filter
Multi-select selection:
- No selection (default): All runs
- Yes: Only runs where escalation occurred
- No: Only runs without escalation
Trigger Type Filter
Multi-select selection:
- No selection (default): All runs
- API: Only runs initiated via API
- Workbench: Only runs initiated via Workbench
- Manual: Only runs initiated manually
Schedule Name Filter
Multi-select dropdown to filter by specific schedule names.
Failure Categories
When an execution fails, the system categorises the failure to aid troubleshooting.
Primary Failure Categories
| Category | Description |
|---|---|
| Out of Scope / Guardrail Violation | Request fell outside the AI Colleague's defined job description or violated guardrail policies |
| Skill/AOP failure : execution error | Skill/AOP failed to execute as expected |
Participation Coverage
Click the Participation Coverage badge on any row to view all participants involved in that execution.
Participant Categories
| Category | Description |
|---|---|
| Initiated For | The individual or entity this run serves |
| Action Owners | Users assigned approval or input tasks during execution |
| Escalation Contact(s) | Users contacted for exception handling and guidance |
Token Tracking
Run History tracks token consumption for cost monitoring and performance analysis.
| Column | Description |
|---|---|
| Input Tokens | Sum of all input tokens across all LLM calls in the run |
| Output Tokens | Sum of all output tokens across all LLM calls in the run |
Token Aggregation Includes:
- Initial Analysis (re-ranking, shortlisting of AOP/Skill)
- Skills/AOP invocations using LLM
- Any AOP step using LLM processing
Note: Runs without LLM invocations display "NA" for token columns.
Column Customisation
Manage Columns
- Click the Edit Columns icon next to the table header
- Check/uncheck columns to show/hide
- Changes apply immediately
Reorder Columns
- Drag and drop column headers to reorder
- Column order preferences persist across sessions
Exporting Data
Export Options
| Format | Description |
|---|---|
| CSV (.csv) | Plain comma-separated values |
Export Behaviour
- Exports current filtered and sorted view
- All columns exported (added through managed columns)
- Maximum 10,000 rows per export
- Exports exceeding 10,000 rows generate a .zip file with multiple files
- Share via Email: Option to send export directly to specified recipients
Updated 5 days ago