Skip to main content
GET
Retrieve an agent

Authorizations

X-API-KEY
string
header
required

Path Parameters

id
string
required

The unique identifier of the agent

Response

Agent retrieved

An agent: standing instructions executed in an isolated sandbox with access to the environment's data, on a schedule or on demand. The same objects the app's Agents page manages.

name
string
required

Unique within the environment

instructions
string
required

The standing prompt every run executes

id
string<uuid>
description
string | null
mentions
object[]

Reconciliations, data streams, users, and other agents whose context is resolved into every run's prompt. Mentioning an agent also teaches the run how to trigger it (see POST /agents/{id}/runs)

model
string

The model the agent runs on — resolved to the platform default when not set explicitly

cadence
enum<string>

manual agents only run when triggered (POST /agents/{id}/runs)

Available options:
manual,
hourly,
daily,
weekdays,
weekly
hour
integer | null

Required for daily, weekdays, and weekly cadences

Required range: 0 <= x <= 23
minute
integer | null

Required for every cadence except manual

Required range: 0 <= x <= 59
day_of_week
integer | null

0 = Sunday. Required for weekly cadence

Required range: 0 <= x <= 6
timezone
string
default:UTC

IANA timezone the schedule is evaluated in

active
boolean

Inactive agents are never scheduled but can still be run on demand

handles_file_drops
boolean

Whether this agent processes files dropped in the app. At most one active agent per environment can have this enabled.

delivery_enabled
boolean

Email output files matching delivery_file_pattern to delivery_recipients after each completed run

delivery_recipients
string<email>[]
delivery_file_pattern
string
default:*.csv

Case-insensitive glob selecting which output files are delivered

input_files
object[]
next_run_at
string<date-time> | null
last_run_at
string<date-time> | null
created_at
string<date-time>
updated_at
string<date-time>