Skip to main content
POST
/
v1
/
agents
Create Agent
curl --request POST \
  --url https://api.example.com/v1/agents \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "name": "<string>",
  "avatar_id": "<string>",
  "system_prompt": "<string>",
  "language": "en",
  "greeting": "Hello!",
  "max_session_length_minutes": 30,
  "capabilities": [
    {
      "type": "webcam_vision"
    }
  ],
  "llm": {
    "type": "openai"
  }
}
'
{
  "id": "<string>",
  "name": "<string>",
  "avatar_id": "<string>",
  "system_prompt": "<string>",
  "language": "en",
  "greeting": "Hello!",
  "max_session_length_minutes": 30,
  "capabilities": [
    {
      "type": "webcam_vision"
    }
  ],
  "llm": {
    "type": "openai"
  }
}

Authorizations

x-api-key
string
header
required

Your Beyond Presence API Key.

Body

application/json

Request body to create an agent.

name
string
required

Display name to use. Also used when addressed in conversations.

Required string length: 1 - 100
Examples:

"Jarvis"

"HAL 9000"

avatar_id
string
required

ID of avatar to use.

Required string length: 1 - 100
Example:

"01234567-89ab-cdef-0123-456789abcdef"

system_prompt
string
required

System prompt to use.

Required string length: 1 - 10000
Example:

"You are a helpful assistant."

language
enum<string> | null

Language to use.

Available options:
ar,
bn,
bg,
zh,
cs,
da,
nl,
en,
en-AU,
en-GB,
en-US,
fi,
fr,
fr-CA,
fr-FR,
de,
el,
hi,
hu,
id,
it,
ja,
kk,
ko,
ms,
no,
pl,
pt,
pt-BR,
pt-PT,
ro,
ru,
sk,
es,
sv,
tr,
uk,
ur,
vi
Example:

"en"

greeting
string | null

What to say when a call starts.

Required string length: 1 - 1000
Example:

"Hello!"

max_session_length_minutes
integer | null

Maximum session length in minutes.

Required range: 0 < x <= 90
Example:

30

capabilities
(WebcamVisionAgentCapability · object | WakeupModeAgentCapability · object)[]

Extra capabilities to manage calls.

Agent capability to see user camera feed.

Example:
[
{ "type": "webcam_vision" },
{
"type": "wakeup_mode",
"triggers": ["hey agent", "hi pal"]
}
]
llm
OpenaiAgentLlm · object

Configuration for LLM to use.

Example:
{ "type": "openai" }

Response

Created Agent with ID

Response model for an agent.

id
string
required

Unique identifier of the object in the database.

Example:

"01234567-89ab-cdef-0123-456789abcdef"

name
string
required

Display name to use. Also used when addressed in conversations.

Required string length: 1 - 100
Examples:

"Jarvis"

"HAL 9000"

avatar_id
string
required

ID of avatar to use.

Required string length: 1 - 100
Example:

"01234567-89ab-cdef-0123-456789abcdef"

system_prompt
string
required

System prompt to use.

Required string length: 1 - 10000
Example:

"You are a helpful assistant."

language
enum<string> | null

Language to use.

Available options:
ar,
bn,
bg,
zh,
cs,
da,
nl,
en,
en-AU,
en-GB,
en-US,
fi,
fr,
fr-CA,
fr-FR,
de,
el,
hi,
hu,
id,
it,
ja,
kk,
ko,
ms,
no,
pl,
pt,
pt-BR,
pt-PT,
ro,
ru,
sk,
es,
sv,
tr,
uk,
ur,
vi
Example:

"en"

greeting
string | null

What to say when a call starts.

Required string length: 1 - 1000
Example:

"Hello!"

max_session_length_minutes
integer | null

Maximum session length in minutes.

Required range: 0 < x <= 90
Example:

30

capabilities
(WebcamVisionAgentCapability · object | WakeupModeAgentCapability · object)[]

Extra capabilities to manage calls.

Agent capability to see user camera feed.

Example:
[
{ "type": "webcam_vision" },
{
"type": "wakeup_mode",
"triggers": ["hey agent", "hi pal"]
}
]
llm
OpenaiAgentLlm · object

Configuration for LLM to use.

Example:
{ "type": "openai" }