rencore.com (opens in a new tab) Start a trial (opens in a new tab)
Reference

ChatGPT agent run

Last updated Preview Inventory ChatGPT Enterprise

AI summary

The ChatGPT agent run object tracks executions of ChatGPT workspace agents, recording who triggered each run, when it started, its outcome, skills used, and external connector calls made. You can identify which runs were autonomous, meaning they were triggered by schedule or webhook rather than by a person. Risk scores and memory operation counts help you monitor agent behavior and identify potential security concerns.

Runs of ChatGPT workspace agents, by trigger type and invoker

Part of the ChatGPT Enterprise inventory.

In Rencore Governance

The ChatGPT Agent Run inventory page in Rencore Governance: counts, trend, violated policies and the list of objects
The inventory page in a Rencore demo Environment, captured October 2026.

Scan settings

Default scanning interval Allowed scanning intervals Data removal during incremental scan
Daily Daily, Weekly, Bi-Weekly, Monthly, Never, Initial No

Properties

Property Type Description Automation placeholder
Agent ChatGPT agent {{ChatGPTAgentRun.Agent}}
Agent Name String {{ChatGPTAgentRun.AgentName}}
Key String Internal. {{ChatGPTAgentRun.ApiKeyEncrypted}}
Connector Calls Int32 How many external connector calls the run made, from its CONNECTOR_CALL_COMPLETED events. {{ChatGPTAgentRun.ConnectorCallCount}}
Initially Scanned DateTime Shows when this object was initially found in a scan. {{ChatGPTAgentRun.CreatedTime}}
Display Name String {{ChatGPTAgentRun.DisplayName}}
Duration (s) Double {{ChatGPTAgentRun.DurationSeconds}}
Run ID String {{ChatGPTAgentRun.Id}}
Invoked By ChatGPT user The person who started the run. Null for schedule and webhook runs, which is exactly the case worth finding. {{ChatGPTAgentRun.InvokedByUser}}
Invoked By Name String {{ChatGPTAgentRun.InvokedByUserName}}
Is Autonomous Boolean True when no human invoker is attached to the run. {{ChatGPTAgentRun.IsAutonomous}}
Last scan update DateTime Shows when this object was last updated in a scan. If an object is found during a scan but no property has been changed this date will not change. {{ChatGPTAgentRun.LastModifiedTime}}
Memory Operations Int32 How many times the run read, wrote or deleted agent memory, from its MEMORY_READ, MEMORY_WRITE and MEMORY_DELETE events. {{ChatGPTAgentRun.MemoryOperationCount}}
Outcome String Allowed values: cancelled, failed, succeeded, timed_out. {{ChatGPTAgentRun.Outcome}}
Risk Score Int32 Stores risk score {{ChatGPTAgentRun.RiskScore}}
Risk Score Update DateTime Stores risk score update {{ChatGPTAgentRun.RiskScoreLastUpdate}}
Risk Score Value String Stores risk score value like Low_Low {{ChatGPTAgentRun.RiskScoreValue}}
Skills Used String Which skills the run invoked, from SKILL_USED events. This is the only way skill usage is visible without reading messages. {{ChatGPTAgentRun.SkillsUsed}}
Started At DateTime When the run began. Bucketed per day for reporting. {{ChatGPTAgentRun.StartedAt}}
Trigger Type String What started the run. Everything other than chatgpt means no person pressed anything. Allowed values: api_trigger, chatgpt, schedule_trigger, webhook_trigger. {{ChatGPTAgentRun.TriggerType}}
Workspace ChatGPT Workspace {{ChatGPTAgentRun.Workspace}}
Workspace Name String {{ChatGPTAgentRun.WorkspaceName}}

Relations

Relation Connector Description
ChatGPT agent ChatGPT Enterprise Agents published into the ChatGPT workspace, with their skills, connectors, run history and spend
ChatGPT user ChatGPT Enterprise Every user in the connected ChatGPT workspace, with role, seat, spend and the Entra ID join
ChatGPT Workspace ChatGPT Enterprise The connected ChatGPT Enterprise workspace, its granted scopes and its coverage gaps

Segments

This object does currently not have any segments.

Actions

This object does currently not have any actions.

Frequently asked questions

What is the ChatGPT agent run object in Rencore Governance?

Runs of ChatGPT workspace agents, by trigger type and invoker. ChatGPT agent run is an object type in the ChatGPT Enterprise inventory of Rencore Governance.

Which properties does Rencore Governance collect for ChatGPT agent run?

Rencore Governance collects 22 properties for ChatGPT agent run, such as Agent, Agent Name, Key and 19 more.

How often is ChatGPT agent run scanned?

By default daily. You can change the scan interval of ChatGPT agent run objects under Configure objects (daily, weekly, bi-weekly, monthly, never or initial (collected once)). The interval is a target, not a guarantee: a scan can run later than planned.

Which module includes the ChatGPT Enterprise connector?

The ChatGPT Enterprise connector is part of the AI & Agents module of Rencore Governance, an add-on module on the Premium and Enterprise Plans. The connector is in preview.

Related pages

Related pages