Business Assist (Preview)
Business Assist connector provides a set of services to automate common customer-success tasks. Customer service leaders, managers and agent personas can use it to reliably predict service-call volumes (to manage staffing levels), cluster customer feedback (to focus on the right investments) and generate self-help solutions for Microsoft 365 product issues. Reduce your organization’s helpdesk cost and provide great customer experience by adopting the same services that power Microsoft Support.
This connector is available in the following products and regions:
Service | Class | Regions |
---|---|---|
Logic Apps | Standard | All Logic Apps regions except the following: - Azure Government regions - Azure China regions - US Department of Defense (DoD) |
Power Automate | Premium | All Power Automate regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
Power Apps | Premium | All Power Apps regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
Contact | |
---|---|
Name | Microsoft |
URL | https://admin.microsoft.com |
[email protected] |
Connector Metadata | |
---|---|
Publisher | Microsoft |
Website | https://microsoft.com |
Privacy policy | https://support.microsoft.com/privacy |
Categories | AI |
The Business Assist APIs are a set of Machine learning based tools developed to help automate common customer success-oriented tasks. They will help customers and partners achieve their goals to reduce costs, more efficiently listen to customers, and respond to their needs more quickly. These tools will allow large scale data analysis to be performed quickly and automatically. The Business Assist APIs give you tools to better understand your customers' wants and needs and respond to them more quickly.
Create Forecast
Customer service organizations need to reliably predict service call volumes to allocate resources and set staffing levels appropriately. Analyzing past trends and volume levels manually is a time-consuming task. Using machine learning can speed up the process considerably. The Business Assist Forecast API brings the ability to quickly and confidently forecast future support case volume based on historical data.
Forecast support case volume allows you to confidently forecast future support case volume based on historical data. To process forecast share input historical support case volume data in the JSON format. You need to share the seasonality based on what cadence you want to get forecast results. You can retrieve the forecast output results in the JSON file format.
Create Text Analytics
Business Assist Text Analytics service can reduce time and operation costs in feedback data analysis for open-text questions significantly. Our APIs conform to REST architectural style and allow for interaction with RESTful web services.
The Topic Clustering helps to identify and cluster similar responses together and highlight the topics that require your attention most. Feedback text analytics allows you to identify key topics and sentiments from large number of free text responses from any customer/employee surveys. Allowing you to understand crucial pain points of your customers and improve the overall experience.
Get Self-help Insights
Organizations can improve their customers' experience by helping users solve issues on their own without ever needing to contact support. Business Assist Self Help helps find self-serve solutions from Microsoft's extensive library of support articles.
Increase end user satisfaction and reduce your helpdesk costs by integrating with Microsoft 365 self-help, created by product teams, and powered by machine learning. M365 self-help combines user intent (how users express their problem) with what we know about users to show the right self-help solution at the right time. It also returns top web search results to increase self-help success.
Prerequisites
You will need the following to proceed:
A Microsoft PowerApps or Microsoft Power Automate plan with custom connector feature. An Azure subscription.
How to get credentials
- You need to have your app registered in Microsoft Entra ID, as APIs used by the connector are secured by Microsoft Entra ID.
- Generate a client secret id, copy that secret value before you close or redirect to another blade.
- You can connect securely with the connector.
Get started with your connector
- Select "Create"
- Select "Automated Cloud Flow".
- Under Triggers select “Manually trigger a flow”.
- Select "New Step".
- Under "Actions" under "Premium" search for Business Assist conenctor.
- Based on the service you want to use, you can select the Forecasting, TextAnalytics or SelfHelp connector.
- Once you have selected the service, you can add the input in json format and click save and test the flow and get the output results.
Common errors and remedies
Highlight any errors that might commonly occur when using the connector (such as HTTP status code errors), and what the user should do to resolve the error.
- HTTP status: 500 a. Submit Request Failed: The request failed because of an internal error. b. Get Status Request Failed: The request failed because of an internal error. c. Get Result Request Failed: The request failed because of an internal error.
- HTTP status: 403 Ensure your application is registered and you are connected with Business Assist connector.
Creating a connection
The connector supports the following authentication types:
Default | Parameters for creating connection. | All regions | Not shareable |
Default
Applicable: All regions
Parameters for creating connection.
This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.
Throttling Limits
Name | Calls | Renewal Period |
---|---|---|
API calls per connection | 100 | 60 seconds |
Actions
Create forecast job |
Submit forecast job to Business Assist. |
Create text analytic job |
Submit text analytic job to Business Assist. |
Get self-help insights |
Get self-help insights from Business Assist. |
Create forecast job
Submit forecast job to Business Assist.
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
Name
|
Name | True | string |
User-defined name for the Forecast job. |
Forecast end date
|
EndDateTime | True | string |
End date for the forecasting. It can be |
Seasonality
|
Seasonality | True | string |
Divide forecasts by time periods for comparison. Select at most two seasonality from (daily, weekly, monthly, quarterly, yearly). |
Include prediction interval
|
IncludePredictionInterval | True | boolean |
Include prediction interval with results. |
History data JSON
|
inputDataJson | True | string |
JSON-formatted version of the historical data. For example, ``[{"Date":"2022-07-01","Ticket":"195","DAO":"20000"},{"Date":"2022-07-02","Ticket":"774","DAO":"20500"}]`. |
Date property name
|
DateTimeColumnName | True | string |
Column header for the column containing data and time information. |
Volume property name
|
VolumeColumnName | True | string |
Column header for the column containing volume data. |
Adjustment property names
|
AdjustmentColumnNames | array of string |
["DAO"] |
|
Special date data JSON
|
SpecialDateDataJson | string |
JSON-formatted string containing special date data. [{"Date":"2021-10-28","Name":"IgniteDay1"}]. |
|
Special date adjustment data JSON
|
SpecialDateAdjustmentDataJson | string |
JSON-formatted string containing adjustments to make on special dates. [{"Date":"2022-10-01","Ratio":"-0.3"}]. |
|
Name of the column in the `specialDateFileName` listing dates for special days and holidays
|
SpecialDateColumnName | string |
Special date column name. |
|
Name of the column in the `specialDateFilename` listing names of special days and holidays
|
SpecialDateEventColumnName | string |
Special date event column name. |
|
Special date adjustment property name
|
SpecialDateAdjustmentColumnName | string |
Name of the column in the special event data describing the adjustments to make. |
Returns
Name | Path | Type | Description |
---|---|---|---|
OperationId
|
OperationId | string |
Job ID, use to get status and results. |
Name
|
Name | string |
User-defined name for the Forecast job. |
Status
|
Status | integer |
Status code of forecast job. |
Diagnostics
|
Diagnostics | string |
Errors or warnings generated during job creation. |
predictions
|
Results.predictions | array of object | |
date
|
Results.predictions.date | string |
Forecast date. |
forecast
|
Results.predictions.forecast | float |
Forecast value. |
low
|
Results.predictions.low | float |
Forecast low. |
high
|
Results.predictions.high | float |
Forecast high. |
Create text analytic job
Submit text analytic job to Business Assist.
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
Name
|
Name | string |
Name of the submitted job. |
|
ReturnOriginalText
|
ReturnOriginalText | boolean |
Returns original text if the flag is set. |
|
ReturnEnglishText
|
ReturnEnglishText | boolean |
Returns English text if the flag is set. |
|
recordId
|
recordId | string |
Unique identifier for a single response item. |
|
text
|
text | string |
The text of a single response item. This may be multiple sentences. |
Returns
Name | Path | Type | Description |
---|---|---|---|
operationId
|
operationId | string |
OperationId of the submitted job. |
status
|
status | integer |
Status of the submitted job. |
diagnostics
|
diagnostics | string |
Errors or warnings generated during job creation. |
result
|
results.result | array of object | |
recordId
|
results.result.recordId | string |
Unique identifier for each individual response item. |
topicId
|
results.result.topicId | integer |
Unique identifier given to each topic cluster. You can query or filter results based on this id. |
topicConfidence
|
results.result.topicConfidence | float |
Confidence of the machine learning models regarding the clustering of the topic. A higher score is more likely to belong to a cluster. |
topicLabel
|
results.result.topicLabel | string |
Text label given to each cluster. |
sentiment
|
results.result.sentiment | string |
Assessment of whether feedback is positive, negative, or neutral. |
originalText
|
results.result.originalText | string |
Original request text submitted to the Create Cluster API request, returned as a part of results response. Optional, depending on the value of returnOriginalText sent with the Create Cluster request. |
englishText
|
results.result.englishText | string |
This property contains the English translation of the original text. For non-English original text records, englishText contains the text translated into English from the original text provided by the user. For English original text records, englishText contains the original text. Optional, depending on the value of returnEnglishText sent with the Create Cluster request. |
Get self-help insights
Get self-help insights from Business Assist.
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
Problem Description
|
QueryText | True | string |
Text of the user's query. |
Locale
|
Locale | True | string |
Locale to use for the solution returned. |
Returns
Name | Path | Type | Description |
---|---|---|---|
solutions
|
solutions | array of object |
Instant answer to the user query. Contains |
title
|
solutions.title | string |
Solution or article title. |
details
|
solutions.details | string |
Preview text of article or content. |
solutionConfidence
|
solutions.solutionConfidence | float |
Algorithmic confidence score of the confidence the solution is relevant to the query. |
webSearchResults
|
webSearchResults | array of object |
Related article from the web search.Contains the |
title
|
webSearchResults.title | string |
Solution or article title. |
details
|
webSearchResults.details | string |
Preview text of article or content. |
url
|
webSearchResults.url | string |
Link to full content of the |
serviceIncidents
|
serviceIncidents | array of object |
Service incidents. |
id
|
serviceIncidents.id | string |
Response id. |
serviceName
|
serviceIncidents.serviceName | string |
Service name. |
issueType
|
serviceIncidents.issueType | string |
Issue type. |
startTime
|
serviceIncidents.startTime | string |
Start time. |
endTime
|
serviceIncidents.endTime | string |
End time. |
lastUpdatedTime
|
serviceIncidents.lastUpdatedTime | string |
Last updated time. |
impactDescription
|
serviceIncidents.impactDescription | string |
Impact description. |
title
|
serviceIncidents.title | string |
Issue title. |
severity
|
serviceIncidents.severity | string |
Issue severity. |
issueStatus
|
serviceIncidents.issueStatus | string |
Issue status. |
isIncidentResolved
|
serviceIncidents.isIncidentResolved | boolean |
Is incident resolved. |