Detect Intent
dialogflow.detect_intent
ActionGoogle Cloudconnection required
Calls the Dialogflow API POST /v2/projects/{p}/agent/sessions/{s}:detectIntent.
Send a text message to a Dialogflow ES agent and get the matched intent.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- OAuth 2.0
- Providers
- Google Dialogflow ES
- Secret shape
- {"client_id", "client_secret", "refresh_token"}
- Config it needs
- project_id, language_code
- Resolved by
- config.connection_id, else node.connection_id
Configuration
4 fields, 2 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.
| Field | Type | Required | Default | Constraints | Example |
|---|---|---|---|---|---|
project_id GCP project id (overrides connection). | string | No | — | — | — |
session_id Conversation session id (e.g. the user/chat id). | string | Yes | — | — | — |
text User message. | string | Yes | — | — | — |
language_code Agent language (overrides connection). | string | No | — | — | — |
Output
One shape.
result
| Field | Type | Example |
|---|---|---|
ok | boolean | — |
response_text Fulfillment text. | string | — |
intent Matched intent display name. | string | — |
intent_name | string | — |
intent_confidence | number | — |
parameters | object | — |
fulfillment_messages | array | — |
query_text | string | — |
all_required_params_present | boolean | — |
{
"all_required_params_present": false,
"fulfillment_messages": [],
"intent": "",
"intent_confidence": 0,
"intent_name": "",
"ok": false,
"parameters": {},
"query_text": "",
"response_text": ""
}Related Google Dialogflow ES nodes
See Detect Intent run in a workflow.
In a technical demo we add the Google Dialogflow ES connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.