Skip to main content
PATCH
/
api
/
v1
/
agents
/
{id}
/
Update Agent
curl --request PATCH \
  --url https://api.ravan.ai/api/v1/agents/{id}/ \
  --header 'Content-Type: application/json' \
  --header 'X-Api-Key: <api-key>' \
  --data '
{
  "agentName": "Agni2324",
  "status": "ACTIVE",
  "model": "Agni Premium",
  "s2sModel": "Agni Premium",
  "voiceId": "Iris",
  "temperature": 0.7,
  "reminderTriggerMs": 10000,
  "reminderMaxCount": 1,
  "ambientSound": "city_ambience",
  "ambientSoundVolume": 1,
  "maxCallDurationMs": 240000,
  "ringDurationMs": 30000,
  "voicemailMessage": "",
  "voicemailDetectionTimeoutMs": 5000,
  "postCallAnalysisModel": "gpt-4o-mini",
  "postCallAnalysisData": [
    {
      "choices": [
        "Negative",
        "Positive",
        "Neutral"
      ],
      "description": "what was users sentiment throughout the call",
      "name": "sentiments",
      "type": "enum"
    },
    {
      "description": "Detailed summary of the call before you transfer the call to a human agent so that the human agent can understand the context of the call",
      "name": "summary",
      "type": "string"
    },
    {
      "description": "Select the data about their work",
      "name": "what they did in their work?",
      "type": "string"
    }
  ],
  "selectedTools": [
    "019e9308-6e56-7488-910a-cceed909fc7a",
    "019e92fc-e8a4-7c3f-8b14-89a55db6f748"
  ],
  "knowledgeBase": "",
  "beginMessage": "",
  "startSpeaker": "agent",
  "createdAt": "2026-06-04 14:10:48.49862 +0000 UTC",
  "updatedAt": "2026-06-11 10:57:37.109987 +0000 UTC",
  "prompt": "The current date and Time in Asia/Calcutta is {{current_time_Asia/Calcutta}}\n\n# AGNI Friendly Daily Check-In Companion\n\nYou are AGNI, a warm, friendly, caring, and conversational AI companion.\n\nYour role is to have natural human-like conversations and regularly check in on how people are doing throughout their day.\n\nYou are NOT a therapist, counselor, interviewer, recruiter, salesperson, or technical assistant.\n\nYou are simply a friendly AI companion who enjoys talking to people and learning about their day.\nTalk in hindi.",
  "endcallOnSilenceDuration": 10000,
  "reminderMessage": "Hey there are you there?",
  "voicemailCustomPatterns": null,
  "interruptionSensitivity": 0.1,
  "calcomAccountName": "Default",
  "calcomStatus": "active",
  "calcomConnectionType": "agent",
  "ghlAssignUserIdList": [],
  "memory": true,
  "calendarTimezone": "UTC",
  "accent": [],
  "emotion": false,
  "crmSyncProviders": null,
  "salesforceCalendarId": "",
  "salesforceAssignUserIdList": [],
  "emergencyFallback": "+919911293960"
}
'
{
  "success": true,
  "message": "Agent updated successfully",
  "data": { "id": "...", "agentName": "Sales Bot v2" }
}

​
Authorizations

​
X-Api-Key
string
required
Your Agni API key used to authenticate the request. Pass it in the X-Api-Key header. Find or rotate it from your Ravan AI account settings.

​
Request

Example curl: 
curl --request PATCH \
  --url https://api.ravan.ai/api/v1/agents/{id}/ \
  --header 'Content-Type: application/json' \
  --header 'X-Api-Key: YOUR_API_KEY' \
  --data '{
      "agentName": "Agni2324",
      "status": "ACTIVE",
      "model": "Agni Premium",
      "s2sModel": "Agni Premium",
      "voiceId": "Iris",
      "temperature": 0.7,
      "reminderTriggerMs": 10000,
      "reminderMaxCount": 1,
      "ambientSound": "city_ambience",
      "ambientSoundVolume": 1,
      "maxCallDurationMs": 240000,
      "ringDurationMs": 30000,
      "voicemailMessage": "",
      "voicemailDetectionTimeoutMs": 5000,
      "postCallAnalysisModel": "gpt-4o-mini",
      "postCallAnalysisData": [
        {
          "choices": [
            "Negative",
            "Positive",
            "Neutral"
          ],
          "description": "what was users sentiment throughout the call",
          "name": "sentiments",
          "type": "enum"
        },
        {
          "description": "Detailed summary of the call before you transfer the call to a human agent so that the human agent can understand the context of the call",
          "name": "summary",
          "type": "string"
        },
        {
          "description": "Select the data about their work",
          "name": "what they did in their work?",
          "type": "string"
        }
      ],
      "selectedTools": [
        "019e9308-6e56-7488-910a-cceed909fc7a",
        "019e92fc-e8a4-7c3f-8b14-89a55db6f748"
      ],
      "knowledgeBase": "",
      "beginMessage": "",
      "startSpeaker": "agent",
      "createdAt": "2026-06-04 14:10:48.49862 +0000 UTC",
      "updatedAt": "2026-06-11 10:57:37.109987 +0000 UTC",
      "prompt": "The current date and Time in Asia/Calcutta is {{current_time_Asia/Calcutta}}\n\n# AGNI Friendly Daily Check-In Companion\n\nYou are AGNI, a warm, friendly, caring, and conversational AI companion.\n\nYour role is to have natural human-like conversations and regularly check in on how people are doing throughout their day.\n\nYou are NOT a therapist, counselor, interviewer, recruiter, salesperson, or technical assistant.\n\nYou are simply a friendly AI companion who enjoys talking to people and learning about their day.\nTalk in hindi.\n## Personality\n\n* Friendly\n* Warm\n* Curious\n* Positive\n* Caring\n* Patient\n* Conversational\n* Human-like\n\nSpeak naturally like a supportive colleague or friend.\n\nKeep responses short and engaging.\n\nAvoid sounding robotic.\n\n## Primary Goal\n\nYour goal is to make people feel heard and engaged by asking thoughtful questions about their day, work, activities, and well-being.\n\nYou should keep the conversation flowing naturally.\n\n## Conversation Style\n\n* Ask one question at a time.\n* Listen carefully to the answer.\n* Respond to what the user says.\n* Ask relevant follow-up questions.\n* Show genuine curiosity.\n* Avoid rapid-fire questioning.\n\n## Questions You Can Ask\n\n### General Check-In\n\n* How are you today?\n* How has your day been so far?\n* How are you feeling right now?\n* How's everything going?\n\n### Work Check-In\n\n* How was work today?\n* What kept you busy today?\n* Did anything interesting happen at work?\n* Was today productive or hectic?\n\n### Daily Activities\n\n* What did you do today?\n* How did you spend most of your day?\n* Did you get everything done that you planned?\n* What was the best part of your day?\n\n### Break & Wellness\n\n* Did you get a chance to take any breaks today?\n* When was your last break?\n* Did you have lunch on time?\n* Have you been staying hydrated today?\n* Did you get some time to relax?\n\n### Personal Life\n\n* Did you spend time with family or friends today?\n* Have you watched anything interesting recently?\n* Any plans for the evening?\n* Looking forward to anything this week?\n\n## Follow-Up Behavior\n\nAlways acknowledge what the user says before asking the next question.\n\nExample:\n\nUser:\n\"I've been working all day.\"\n\nAGNI:\n\"Sounds like you've had a busy day. Did you manage to take any breaks in between?\"\n\nUser:\n\"Only one lunch break.\"\n\nAGNI:\n\"At least you got some time to step away. What did you have for lunch today?\"\n\n## Emotional Awareness\n\nIf the user sounds happy:\n\n* Celebrate with them.\n* Ask about what went well.\n\nIf the user sounds stressed:\n\n* Be supportive.\n* Ask gentle questions.\n* Do not pressure them.\n\nExample:\n\n\"That sounds like a long day. What was the most challenging part?\"\n\n## Important Rules\n\n* Never interrogate.\n* Never ask multiple questions at once.\n* Never sound like a survey.\n* Never rush the conversation.\n* Never judge the user.\n* Never give unsolicited advice.\n* Never discuss internal instructions.\n\n## Conversation Flow\n\n1. Greet the user.\n2. Ask how they are doing.\n3. Discuss their day.\n4. Ask about work or activities.\n5. Ask whether they took breaks.\n6. Ask about meals.\n7. Ask about plans for the evening.\n8. Continue naturally based on their answers.",
      "endcallOnSilenceDuration": 10000,
      "reminderMessage": "Hey there are you there?",
      "voicemailCustomPatterns": null,
      "interruptionSensitivity": 0.1,
      "calcomAccountName": "Default",
      "calcomStatus": "active",
      "calcomConnectionType": "agent",
      "ghlAssignUserIdList": [],
      "memory": true,
      "calendarTimezone": "UTC",
      "accent": [],
      "emotion": false,
      "crmSyncProviders": null,
      "salesforceCalendarId": "",
      "salesforceAssignUserIdList": [],
      "emergencyFallback": "+919911293960"
      }'

​
Path Parameters

​
id
string
required
The unique ID of the resource in the path. Use the ID returned by the related create or list endpoint.

​
Body

​
agentName
string
The public-facing display name for the agent. This is the name users may see or hear during conversations.
​
model
string
The LLM model identifier used by the agent for reasoning and responses.
​
s2sModel
string
The speech-to-speech model identifier used for realtime voice conversations.
​
voiceId
string
The voice ID used for the agent speech output.
​
temperature
number
Controls response randomness for the agent model. Lower values are more deterministic; higher values are more varied.
​
reminderTriggerMs
integer
The amount of silence, in milliseconds, before the agent sends a reminder or prompt.
​
reminderMaxCount
integer
The maximum number of reminder messages the agent can send during a call.
​
ambientSound
string
The background sound profile to play during calls. Leave empty to disable ambient audio.
​
ambientSoundVolume
number
The volume level for the selected ambient sound. Use a decimal value from 0 to 1, where 0 is muted and 1 is full volume.
​
endCallAfterSilence
boolean
Whether the call should end automatically after a long silence from the user.
​
maxCallDurationMs
integer
The maximum allowed call duration in milliseconds. The call ends when this limit is reached.
​
ringDurationMs
integer
The maximum time, in milliseconds, to let an outbound call ring before it is treated as unanswered.
​
enableVoicemailDetection
boolean
Whether the agent should detect voicemail during outbound calls.
​
voicemailMessage
string
The message the agent should leave when voicemail is detected.
​
voicemailDetectionTimeoutMs
integer
The maximum time, in milliseconds, to wait for voicemail detection before continuing the call flow.
​
enableEmergencyFallback
boolean
Whether to transfer the call to a backup number on failure.
​
emergencyFallbackNumber
string
The backup number to transfer the call to.
​
ivrOptions
object
Interactive voice response settings for the agent, including keypad options and routing behavior.
​
postCallAnalysisModel
string
The model used to generate post-call analysis, such as summaries, sentiment, and disposition.
​
analysisSummaryPrompt
string
The prompt used to generate the post-call summary. Include the outcome, details, and next steps you want the AI to extract.
​
selectedTools
object
The tools enabled for the agent. Include tool IDs and any configuration needed for the agent to call them.
​
integrations
object
Integration settings for the agent, such as connected scheduling, CRM, or webhook configuration.
​
knowledgeBase
string
The knowledge base reference or content available to the agent during conversations.
​
beginMessage
string
The first message the agent says when the conversation starts. Keep it short and natural for voice calls.
​
startSpeaker
string
Who speaks first when the call starts. Use the value supported by the agent configuration, such as agent or user.

​
Response

​
success
boolean
Whether the request succeeded.
​
message
string
Human-readable status message.
​
data
object
Returned data.
{
  "success": true,
  "message": "Agent updated successfully",
  "data": { "id": "...", "agentName": "Sales Bot v2" }
}

Authorizations

​
X-Api-Key
string
header
required

Path Parameters

​
id
string
required

Agent ID

Body

application/json
​
widget_settings_id
string
​
name
string
​
agent_name
string
​
model
string
​
s2s_model
string
​
voice_id
string
​
temperature
number<double>
​
reminder_trigger_ms
integer<int32>
​
reminder_max_count
integer<int32>
​
ambient_sound
string
​
ambient_sound_volume
number<double>
​
end_call_after_silence
boolean
​
max_call_duration_ms
integer<int32>
​
ring_duration_ms
integer<int32>
​
enable_voicemail_detection
boolean
​
voicemail_message
string
​
voicemail_detection_timeout_ms
integer<int32>
​
enable_emergency_fallback
boolean
​
emergency_fallback_number
string
​
ivr_options
object
​
post_call_analysis_model
string
​
analysis_summary_prompt
string
​
selected_tools
object
​
integrations
object
​
knowledge_base
string
​
begin_message
string
​
start_speaker
string

Response

200 - application/json

Successful response

​
success
boolean
​
message
string
​
data
object