Skip to main content
An issue flag should identify a specific conversation that needs review and explain why. Keep the observation, expected behavior, and next reviewer separate from an automated decision about severity.
flag_issue is not an accepted built-in tool type in the current API. This guide does not establish automatic issue detection, ticket creation, notifications, or callbacks during a conversation.

Review an existing conversation

1

Inspect the record

Use conversation inspection and Get conversation details. Confirm the conversation and agent identifiers before recording a concern.
2

Describe the evidence

Record the relevant turn or event, what you expected, and what the stored record shows. Distinguish an unavailable tool from an incorrect answer. Keep unnecessary private information out of review notes.
3

Use a tag for categorization

If your workspace uses review tags, Add tag to conversation accepts a tag_ids list. Use existing tag identifiers from the same workspace. Repeated assignments are ignored; a tag is a category, not a notification or an assigned ticket.
4

Record feedback separately

Send conversation feedback accepts feedback with like, dislike, or null. It does not accept an arbitrary issue title, severity, or reviewer assignment. Do not confuse a negative rating with a complete incident record.

Prepare a future issue process

Keep this process in your existing review system until a supported integration is available. Do not tell a user that a ticket was created or someone was notified unless the responsible service confirms it.

Frequently asked questions

No notification behavior is established by the tag operation. It categorizes the stored conversation. Configure and verify any separate review or notification process independently.
No. It is not an accepted system-tool type. Use the existing conversation-management operations for manual review instead of inventing a tool definition.