A new public API feature (AI App) is now allowing API integration with Diabolocom CCaaS.
New API request parameter diabolocom_call_id (String) is introduced to match Diabolocom Call ID
Dedicated behavior is performed for DIabolocom Call recording access, among with call details retrieval, and their storage in AI task results and AI phone call metadata
Explore AI Public API documentation for more details :
Sample use case : Public API integration within Diabolocom CCaaS scenario
Public API integration within Diabolocom CCaaS scenario - Custom scenario setupPublic API integration within Diabolocom CCaaS scenario - Webservices block setup
The Public API documentation link is also available in AI App home page and AI models pages.
Description :
Parameters required for API use
Endpoints and requests description
Query parameters
Request headers
Request body type and content parameters
Response body type and content parameters
Example requests
(1) Audio -> Dedicated for audio streams
(A) Endpoints description
api/job/tasks | form-data -> Run AI task based on audio (form-data payload) : Relevant for Standalone use case (audio file import)
api/job/tasks | json -> Run AI task based on audio (json payload) : Relevant for Public API Integration with Diabolocom CCaaS (voice) (for performing AI analyses on existing transcription job)
A new release is deployed for AI CDN Frontend on March 17, 2025 (4:00 PM UTC).
Release name : ai-cdn-2025.3.1
Release scope : AI CDN Frontend
Release repository : ai-components
Release date : March 17, 2025 (4:00 PM UTC)
Release platform(s) : Production
Web Components details :
Component : ai-details-pane
Version : 0.0.6
Release content :
FEATURE : Implemented a polling system for the ai-insights web component when the job status is queued or transcript-available. The system will retry requests every 30 seconds for up to 2 minutes 30 seconds to improve responsiveness
FEATURE : Integrated the job_status attribute from ai-core-api to manage ai-insights web component status updates and display handling. The supported statuses include :
A new release is deployed for AI App Frontend on March 17, 2025 (4:00 PM UTC).
Release name : ai-app-front-2025.3.1
Release scope : AI App Frontend
Release date : March 17, 2025 (4:00 PM UTC)
Release platform(s) : Production
Release content :
FEATURE : Implemented a CDN for web components to enhance performance and scalability
FIX : Improved handling of large audio files on the model page
LEGACY : Removed the agents_performances_enabled boolean flag, replacing it with a feature toggle: agents-performances (for display use), now provided by ai-core-api
A new release is deployed for AI Core API on March 17, 2025 (4:00 PM UTC).
Release name : ai-core-api-2025.3.2
Release scope : AI Core API (Web Backend of AI App)
Release date : March 17, 2025 (4:00 PM UTC)
Release platform(s) : Production
Release content :
FEATURE : Added improvement for phone calls listing : Returns phone call as soon as transcript is available ("Reports and Analyses" page) (old behavior : Only the list of phone calls with successful analyses was returned)
FEATURE : Added a new phone call attribute job_status relative to AI task job status (for display use)
LEGACY : Deleted the boolean agents_performances_enabled by using a Feature Toggle instead agents-performances (for display use)
ENV : Changed env platform to a more intuitive name for API Core production (ai-core-api-production)
MIGRATION : Performed a migration to have deletion of usages on an account when the account is deleted
A new release is deployed for AI Core API on February 27, 2025 (7:00 PM UTC).
Release name : ai-core-api-2025.2.3
Release scope : AI Core API (Web Backend of AI App)
Release date : February 27, 2025 (7:00 PM UTC)
Release platform(s) : Production
Release content :
FEATURE : Added the capability to use Engage calls with our Public API endpoint for API integration with Diabolocom CCaaS -> Dedicated documentation and release note will be published soon !
FEATURE : Added documentation url used for display of multi-modal models (Markdown not yet updated)
FIX : Single API call to Engage to retrieve agent and call info (instead of multiple calls)
FIX : Fixed a bug on call retrieval that wasn't matched to a specific AI account (improve legacy behavior)
MIGRATION : diabolocom_account_uuid added to our AI accounts + diabolocom_account_id corrected (not applied for AI accounts with only account_identifier)
A new private API is now available for Diabolocom internal stakeholders to update an existing AI enterprise account.
For Diabolocom Customers, that have an existing AI Enterprise Account, there is an internal need to update AI account information and setup its parameters, as well as account level features configuration.
API use by Project Manager / Account Manager
This API has the following features :
Updating AI account parameter ccaas_platform, used for AI public API for non native integration with Diabolocom CCaaS
Updating AI account parameter ccaas_token, used for AI public API for non native integration with Diabolocom CCaaS
More update capabilities will come in the future, according to upcoming account level features, and their setup requirements.
The private API to create AI enterprise account linked to CCaaS account, has evolved to include the following changes :
More explicit request payload parameters names
user_email instead of email (deprecated)
user_password instead of password (deprecated)
ccaas_token instead of token (deprecated) -> CCaaS public API token with relevant permissions, required for AI public API (Public API - non native integration with Diabolocom CCaaS)
A new request payload parameter (required) : ccaas_platform -> CCaaS platform, required for AI public API (Public API - non native integration with Diabolocom CCaaS)
New private API to identify an existing AI enterprise account
A new private API is now available for Diabolocom internal stakeholders to identify an AI account and have account identification information, to be able to use features such as creating users, tracking account usage, defining account warning/blocked usage thresholds.
This API has the following features :
Identifying an AI account using an account identifier
Identifying an AI account using any related user email address
As a result, AI account main identification information is returned : AI account UUID, creation date, identifiers.
Example request of new private API (case of using an account identifier)
Example request of new private API (case of using a related user email address)
Token delivery process improvement
To be able to run AI private API (internal use only), Tokens requests are made depending on the scope (to create AI account, to create user to AI account, to identify an account, to track an account usage, to define AI account warning/blocked usage thresholds).
Tokens creation and delivery used to be performed by a single person, thus causing reactivity issues.
An internal API is deployed to allow any member of AI Dev team (that have permission) to generate and deliver Tokens to Diabolocom internal stakeholders.
We made some adjustments on the evaluation methods of our models. We are starting to use a more statistics-oriented approach to have even better precision, and we adapted the prompting techniques to make sure the model is more efficient.
As a result, most of the issues linked to both reasoning <> option chosen coherency and non applicability have been fixed.
Release of the first public API Endpoints for the Diabolocom QM
It is now possible to request via API a filtered list of interactions and the details of a single interaction. Available contents are both the QM analysis and the AI analysis (summary, tags etc).
A new page called "My account" was created to manage authentication tokens in order to access the Public API. On that page you can create a token to authenticate your requests.
On each endpoint you can filter by multiple fields, from interaction date, brands and channels to language, scoring duration and many more.
This is very useful for clients to extract QM interactions data, along with AI analyses, for data analysis and automation processes (BI, integrations...)
The complete documentation is available in Clickup or as a Postman collection there.
Get QM Interactions list Get QM detailed interaction by ID
Quality of life updates
We now display the payload format when configuring actions.
Payload format
We reworked the user table to make it display the user ID (and not the internal ID), and changed the order of the columns.
We changed the names of the AI analysis sections to make it more human friendly and removed references to sentiments.