API Dokumentation
ticket
- GETGet next ticket id to work on
- POSTGet a list of tickets
- POSTCreate a ticket
- PATCHUpdate a few tickets at once
- GETGet a ticket
- PATCHUpdate a ticket
- GETGet ticket variables
- GETGet a tickets history
- POSTForward a ticket
- POSTAuto-execute a ticket
- GETPing a ticket
- GETGet ticket activity
- GETGet ticket stats
- GETGet agent queue status
customer
intent
aiAgent
- GETList of all available AI agents as an array
- GETList of all available AI agents as an tree based on associated tag
- POSTLoad enneo default AI Agents
- POSTCreate a new aiAgent
- GETGet an AI Agent by id
- DELDelete an existing AI Agent
- PATCHUpdate an existing AI Agent
- GETGet similar tickets for an AI Agent
- POSTPreview an AI Agent
- POSTGet the outcome of an AI Agent
aiQualityCheck
- GETGet all test runs with pagination
- POSTSchedule a new AI quality check
- GETGet a specific test run by ID
- DELDelete a specific test run by ID
- PATCHUpdate the expected result of a test ticket
- PATCHAccept the expected result of a test ticket
- POSTAccept ALL the expected results of for a test run
- GETGet all AI agents for which test runs can be triggered
- GETGet all AI agents for which test runs can be triggered
- GETGet test cases by AI agent ID
- POSTAdd test cases for an AI agent
- DELDelete a test case by ID
- PATCHUpdate a test case by ID
intentTemplate
profile
team
reminder
settings
- GETGet settings of a client
- POSTUpdate multiple settings at once
- GETGet settings of a client and return the results in a compact form
- GETGet settings of a client in a grouped way for a category
- PUTUpdate setting
- GETSearch settings
- GETGet Subchannels
- POSTAdd a new Subchannel
- DELDelete a Subchannel
- GETGet User Defined Functions
- POSTAdd a new User Defined Function
- DELDelete a User Defined Function
- GETRedirect to Microsoft authorization page
- GETCallback for Microsoft authorization
tag
cron
version
knowledgeSourceStructure
knowledgeSource
pcProxy
cortex
Get intent(s) detected/assigned for a ticket
curl --request GET \
--url https://demo.enneo.ai/api/mind/intent/byTicketId/{ticketId}
{
"ticketId": 376189,
"intentsFound": 1,
"aiOutcome": "agentAssist",
"intents": [
{
"id": 1211221,
"code": "process_meter_reading",
"name": "Process a meter reading",
"contractId": 746839,
"confidence": 0.95,
"confidenceColor": "warning",
"verified": false,
"context": {},
"messagePreview": "We have successfully processed your meter reading",
"recipient": "john@smith.com",
"tags": "prePopulated",
"data": {},
"options": [
{
"type": "enter_into_system",
"name": "Eintragen",
"icon": "check",
"recommended": true,
"order": 1
},
{
"type": "ignore",
"name": "Ignorieren",
"icon": "cancel",
"recommended": false,
"order": 2
},
{
"type": "forward_to_vnb",
"name": "An VNB verweisen",
"icon": "questionMark",
"recommended": false,
"order": 3
}
],
"infos": [
{
"type": "warning",
"message": "Reading is plausible",
"extraInfo": "Expected reading was 421 kWh. Plausbible because difference to 317 kWh is below threshold of 200 kWh"
}
],
"extraInfo": null,
"outcome": {
"aiAgentId": 1,
"success": true,
"messageLocalized": "Powercloud accepted meter reading",
"internalData": {
"requestEndpoint": "saveReadingByContractId",
"requestParams": "readingValue=21;date=2022-12-31"
},
"executedAt": "2022-12-13 22:18:06",
"userId": 1,
"sent": true,
"ticketClosed": true,
"recipient": "john@smith.com",
"message": "We successfully processed your meter reading of 21 kWh dated Dec 31, 2022",
"template": "<p>Dear John,</p><p>%MESSAGE%</p><i>Mike from your service team</i>",
"sources": [
{
"type": "knowledgeSource",
"id": 376189,
"name": "Opening hours",
"url": "https://company.com/faq/376189",
"text": "Our service hours are from 8am to 5pm. We are closed on weekends. [...]"
}
],
"txId": "c916167c94"
}
}
]
}
Authorizations
Cookie-based authentication
Path Parameters
The id of the ticket for which the intents should be retrieved
Response
Number of intents found
Outcome of the AI's detected processing 1) noDetection: AI did not find anything useful 2) customerDetected: AI detected the customer, but nothing else 3) agentAssist: AI detected an intent, but is not confident enough to excecute it without additional support 4) full: AI fully resolved the issue. No agent interaction needed any more
noDetection
, customerDetected
, agentAssist
, full
An intent of a customer that he wants to be resolved by contacting us
Internal ID of intent
Intent model code that resolves a specific issue. Currently supported is process_meter_reading, process_bank_data and process_installment_change
User-readable name of intent as defined by client
Confidence how certain the AI is that this is correct. 0.95 means for example 95% certain. Defaults to 100% when verified by human.
A color indication of an intent showing the user how much user interaction is needed. 'success' indicates the AI is ready to execute, all other codes require user interaction first
success
, neutral
, warning
, danger
True if intent has been verified by human
Intent-specific additional data to be shown to the user so he has relevant information about the intent. Data type varies by intent code
A preview of the response a customer would receive when executing this intent. Not always available, e.g. when the respond depends on user-input
Tags to show to the user. prePopulated means that all properties are already pre-filled by the AI and the user can just insert the template to the body. adaptionNeeded is the opposite, and means the user still needs to modify the text. writesToErp means that upon execution of the intent a write is done to the ERP system, like a insertion of a meter reading or the creation of a bill.
prePopulated
, adaptionNeeded
, writesToErp
Intent-specific data object showing all the data that was extracted from the ticket in a structured form. Data type varies by intent code
Extra-Information shown in tooltip. Info-Icon only shown if not null
Shows the outcome (if the intent was already executed)
ID of the AI agent that was executed
Human-readable message, usually from the backend system. Already localized.
Technical output for debugging purposes
Date and time when intent was executed
User ID of user that triggered the intent. 0 for system user
Was the email / chat message / etc. described in this object successfully sent?
Was the ticket closed?
Any sources that were used to create the result
A source that was used by an AI model / intent
The type of source used. ticket = A similar ticket existed and that response was used as a basis knowledgeSource = An external knowledge source was used, usually a company Wiki or FAQ template = A predefined text template could be applied languageModel = If the AI model did not use anything end created the answer by itself
ticket
, knowledgeSource
, template
, languageModel
Reference to the entry id, e.g. ticketId (if type=ticket)
Name of reference (e.g. FAQ title or ticket title)
URL to associated source. null for sources with internal ids (tickets and templates) or if non-existant (language model source)
Full text that was used as source
Unique transaction id. Corresponds to a log entry in enneo
curl --request GET \
--url https://demo.enneo.ai/api/mind/intent/byTicketId/{ticketId}
{
"ticketId": 376189,
"intentsFound": 1,
"aiOutcome": "agentAssist",
"intents": [
{
"id": 1211221,
"code": "process_meter_reading",
"name": "Process a meter reading",
"contractId": 746839,
"confidence": 0.95,
"confidenceColor": "warning",
"verified": false,
"context": {},
"messagePreview": "We have successfully processed your meter reading",
"recipient": "john@smith.com",
"tags": "prePopulated",
"data": {},
"options": [
{
"type": "enter_into_system",
"name": "Eintragen",
"icon": "check",
"recommended": true,
"order": 1
},
{
"type": "ignore",
"name": "Ignorieren",
"icon": "cancel",
"recommended": false,
"order": 2
},
{
"type": "forward_to_vnb",
"name": "An VNB verweisen",
"icon": "questionMark",
"recommended": false,
"order": 3
}
],
"infos": [
{
"type": "warning",
"message": "Reading is plausible",
"extraInfo": "Expected reading was 421 kWh. Plausbible because difference to 317 kWh is below threshold of 200 kWh"
}
],
"extraInfo": null,
"outcome": {
"aiAgentId": 1,
"success": true,
"messageLocalized": "Powercloud accepted meter reading",
"internalData": {
"requestEndpoint": "saveReadingByContractId",
"requestParams": "readingValue=21;date=2022-12-31"
},
"executedAt": "2022-12-13 22:18:06",
"userId": 1,
"sent": true,
"ticketClosed": true,
"recipient": "john@smith.com",
"message": "We successfully processed your meter reading of 21 kWh dated Dec 31, 2022",
"template": "<p>Dear John,</p><p>%MESSAGE%</p><i>Mike from your service team</i>",
"sources": [
{
"type": "knowledgeSource",
"id": 376189,
"name": "Opening hours",
"url": "https://company.com/faq/376189",
"text": "Our service hours are from 8am to 5pm. We are closed on weekends. [...]"
}
],
"txId": "c916167c94"
}
}
]
}