WorkflowRun event log

Glean Assistant and Glean Agents interactions run as workflows. The WorkflowRun event type in Glean Customer Event Logs captures each top-level workflow invocation as a single, well-structured entry, giving you comprehensive visibility into usage across Glean AI products — including agents, AI Answers, Summarization, Deep Research, Daily Digests, and more.

Because it consolidates all relevant execution data in one place, WorkflowRun makes analysis of assistant usage, agent activity, and AI-driven features simpler, more reliable, and more performant.

The following users might be interested in the WorkflowRun event log:

• Admins: Managing analytics pipelines, log integrations, and product dashboards
• Data and business analysts: Building queries or KPI dashboards from Glean event logs
• Developers and IT: Who join Glean logs with other systems or manage feature adoption
• End users: Relying on metrics or dashboards powered by workflow data

Key fields in WorkflowRun

Each WorkflowRun event includes:

• runId: Globally unique identifier for the top-level workflow invocation
• chatSessionId and sessionTrackingToken: Links to the user session context

• feature: Indicates the Glean capability used (for example, AI_ANSWER, DAILY_DIGESTS, AGENT)
• initiator: Source of execution (for example, USER, SYSTEM, AUTOMATION, EVAL)
• platform: Where the workflow originated (for example, WEB or REST_API)

• workflowExecutions: Includes workflow-level IDs, namespaces (for example, AGENT or STATIC_WORKFLOW), and execution status
• stepExecutions: Captures granular information about steps, status, errors, tools used, and citations

info

For a detailed description of these fields, see Event schemas.

Relationship to Chat and Workflow logs

Glean AI usage spans these event types:

• CHAT: Base chat turns, including interactions from surfaces such as Slack. Use this event type for chat-volume and chat-response analysis.
• HUMAN_ONLY_CHAT_MESSAGE: Metadata for user-authored chat messages, without the assistant response.
• WORKFLOW_RUN: Comprehensive workflow tracking. Use this event type for workflow, agent, and AI-feature metrics; it does not replace CHAT for all chat analytics.
• WORKFLOW (Deprecated): Replaced by WORKFLOW_RUN. Doesn't receive new data.

Workflow Deprecation

WorkflowRun became the source of truth for workflow metrics when it replaced the Workflow log in June 2025. If you analyze historical data that spans that cutover, join across Chat, Workflow, and WorkflowRun to get complete workflow metrics for that period. For data after the cutover, use WorkflowRun for workflow metrics, while continuing to use CHAT and HUMAN_ONLY_CHAT_MESSAGE for chat analytics. See Insights production queries for stitching queries that cover the transition.

Common use cases

• Agent usage analysis: Track user engagement with custom agents.
• Agent usage analysis: Track user engagement with custom agents
• AI feature adoption: Monitor usage of AI Answers, Summarization, and more
• Performance monitoring: Analyze workflow execution times and success rates
• User behavior insights: Understand how users interact with AI features
• Performance monitoring: Analyze workflow execution times and success rates.
• User behavior insights: Understand how users interact with AI features.

See Insights production queries for detailed examples of working with WorkflowRun data.

Frequently asked questions

See Insights production queries for example queries that consume this event type.

No. WorkflowRun contains only data generated after it replaced the Workflow log. To analyze earlier periods, join across Chat, Workflow, and WorkflowRun.

Filter on initiator = 'USER'. The feature, namespace, or workflow_id fields can further segment by workflow type.

Named IDs are Glean-provided or default workflows. Random-appearing IDs are custom or user-defined.

See Event schemas for schema definitions and Insights production queries for query examples.

See also

• Overview
• Event schemas
• Insights production queries

Need help?

Still have questions or want implementation advice? Reach out to your Glean admin.