For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
A thread is a container that holds the context and history for agent work. Threads are commonly associated with a specific context such as a business_id and persist across multiple runs.
Thread object
Example JSON response
1
{
2
"object": "thread",
3
"id": "b1c2d3e4-5678-90ab-cdef-1234567890ab",
4
"created_at": "2026-01-15T12:00:00.000Z",
5
"updated_at": "2026-01-15T12:30:00.000Z",
6
"status": "completed",
7
"metadata": null,
8
"requester": null,
9
"steps": []
10
}
Thread attributes
Attribute
Type
Description
object
string
Object type identifier. Always thread.
id
string (uuid)
Unique identifier for the thread.
created_at
string (date-time)
ISO 8601 timestamp of when the thread was created.
updated_at
string (date-time)
ISO 8601 timestamp of when the thread was last updated.
status
string
Current lifecycle status. One of running, completed, error, or interrupted.
metadata
object | null
Internal metadata associated with the thread.
requester
object | null
Requester context associated with the thread.
steps
Step[]
Execution steps emitted by the underlying agent state. Only included when requesting thread details with step state. See Step attributes.
Status values
Status
Description
running
The thread is active and processing a run.
completed
All runs in the thread have completed.
error
A run in the thread encountered an error.
interrupted
A run in the thread has paused and is waiting for input.
Get a demo
Contact your account manager or contact sales to inquire about access.
