Skip to main content
PUT
/
api
/
v1
/
agents
/
{agent_id}
/
flow
# Switch to llm_driven mode
curl -X PUT "https://app.talkover.ai/api/v1/agents/agent-uuid/flow" \
  -H "Authorization: Bearer talq_your_environment_token_here" \
  -H "Content-Type: application/json" \
  -d '{ "conversation_mode": "llm_driven" }'

{
  "success": true,
  "data": {
    "conversation_mode": "flow_driven",
    "flow_config": { ... }
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.talkover.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Update Agent Flow

Update an agent’s conversation mode and (when applicable) the structured flow configuration. Submitting an invalid flow returns a 422 with details — use Validate Agent Flow to dry-run validation before saving.

​
Endpoint

PUT /api/v1/agents/{agent_id}/flow

​
Path Parameters

​
agent_id
string
required
Agent UUID.

​
Request Headers

​
Authorization
string
required
Bearer token. Format: Bearer talq_your_environment_token_here
​
Content-Type
string
required
Must be set to application/json

​
Request Body

​
conversation_mode
string
required
Conversation mode. Options:
  • llm_driven — LLM-guided conversation (knowledge + actions). Send flow_config: null or omit.
  • flow_driven — node-graph driven. flow_config is required.
​
flow_config
object
Flow definition. Required when conversation_mode is flow_driven.

​
Examples

# Switch to llm_driven mode
curl -X PUT "https://app.talkover.ai/api/v1/agents/agent-uuid/flow" \
  -H "Authorization: Bearer talq_your_environment_token_here" \
  -H "Content-Type: application/json" \
  -d '{ "conversation_mode": "llm_driven" }'

​
Response

{
  "success": true,
  "data": {
    "conversation_mode": "flow_driven",
    "flow_config": { ... }
  }
}

​
Error Responses

​
422 — Invalid Flow

{
  "success": false,
  "message": "Flow validation failed",
  "errors": [
    "initial_node_id 'node-greet' not found in nodes",
    "Node 'node-qualify' references unknown next node 'node-bookx'"
  ]
}

​
Notes

  • Updating the flow does not change the agent’s status — but published agents need to be re-published if the flow change is breaking.
  • See List Flow Versions to track historical configurations.