Artificial intelligence in Pega Sales Automation™ helps you to proactively assess risks on deals in the pipeline, coach newly recruited sales representatives, and identify leads that have a high probability to be converted to opportunities.

Before using artificial intelligence insights with Pega Sales Automation, activate the feature for your implementation and then configure the application to train Pega’s adaptive models for artificial intelligence.

To configure your application for artificial intelligence, log in to Pega Sales Automation and complete the following steps:

• Activate artificial intelligence
• Verify Decision Strategy Manager (DSM) nodes
• Import historical data
• Truncate data sets
• Delete existing models
• Run the data flows for opportunity insights
• Run the data flows for sales coach
• Optional: Run the data flows for lead ranking (B2B selling mode)
• Optional: Run the data flows for lead ranking (B2C selling mode)
• Enable preloaded NBAs

Activating artificial intelligence

1. In the App Studio Explorer panel, click Settings > Application Settings.
2. On the Features tab, select the Artificial intelligence insights - opportunity insights, lead ranking, and sales coach check box to see all the AI capabilities.
3. Enable any of the listed AI capabilities by selecting the individual check box.
4. Click Save.
5. In the header of App Studio, click the Switch Studio menu and then click Dev Studio.
6. In Dev Studio, open the SA-Artifacts agent schedule.
7. On the Edit Agent screen, select the Enabled? check box for all scheduled agents.
8. Click Save.

Verifying Decision Strategy Manager (DSM) nodes

1. In Dev Studio, click Configure > Decisioning > Infrastructure > Services.
2. Verify that each of the following services contains a node with a status of Normal:
   • Decision Data Store
   • Adaptive Decision Manager
   • Data Flow
   • Visual Business Director

Importing historical data

1. In Dev Studio, click Configure > Application > Distribution > Import.
2. Click Choose File, browse for and select the HistoricalData file from your distribution media, and then follow the wizard instructions.
   Pega-provided historical data consists of a snapshot of data from a production environment for various models.

Truncating data sets

1. In the Dev Studio header search text field, search for and select the pxDecisionResults data set of the Data-Decision-Results class.
2. Click Actions > Run.
3. In the Operations field, select Truncate.
4. Click Execute.
5. Repeat steps 1 through 4 for the PreviousStages data set of the SA-SR class.

Deleting existing models

1. In Dev Studio, click Configure > Decisioning > Predictive Analytics > Adaptive Models Management.
2. Select all of the existing models:
   • PredictWin
   • PredictMoveNextStage
   • PredictCloseDate
   • BaseWinModel
   • LeadRanking
   • PredictEffectiveness
3. Click Delete Models

Running the data flows for opportunity insights

Run the data flows for opportunity insights to pass the incoming data to the adaptive models so that the system can calculate opportunity insights.

1. In the Dev Studio header search text field, search for and select the StoreOpportunitySnapshots data flow.
2. Click Actions > Run.
3. On the Data flow test run form, click Start.
4. After you see the confirmation message with a successful result, repeat steps 1 through 3 for the TrainFromHistory data flow.

Running the data flows for sales coach

Run the data flows for the sales coach to pass the incoming data to the adaptive models so that the system can calculate sales coach suggestions.

1. In the Dev Studio header search text field, search for and select the StoreSalesRepSnapshots data flow.
2. Click Actions > Run.
3. On the Data flow test run form, click Start.
4. After you see the confirmation message with a successful result, repeat steps 1 through 3 for the CaptureEffectivenessOutcomes data flow.

Optional: Running the data flows for lead ranking (B2B selling mode)

Run the data flows for lead ranking to pass the incoming data to the adaptive models so that the system can calculate the B2B lead scores.

1. In the Dev Studio header search text field, search for and select the StoreLeadSnapshots data flow.
2. Click Actions > Run.
3. On the Data flow test run form, click Start.
4. Repeat steps 1 through 3 for the CaptureLeadOutcomes data flow.
5. To set up predictors and calculate lead score for already existing leads and store them in the lead predictor table, run the InitialiseLeadPredictorTable activity.

Optional: Running the data flows for lead ranking (B2C selling mode)

Run the data flows for lead ranking to pass the incoming data to the adaptive models so that the system can calculate the B2C lead scores.

1. In the Dev Studio header search text field, search for and select the StoreIndividualLeadSnapshots data flow.
2. Click Actions > Run.
3. On the Data flow test run form, click Start.
4. Repeat steps 1 through 3 for the CaptureIndividualLeadOutcomes data flow.
5. To set up predictors and calculate lead score for already existing leads and store them in the lead predictor table, run the InitialiseLeadPredictorTable activity.

Enabling preloaded NBAs

1. Set usePreloadedNBA dynamic system setting to true.
2. Override the GenerateNBA job scheduler and set the Enable job scheduler toggle to true.
   To see the job scheduler changes instantly, run the LoadNBAForAllOpps dataflow.
3. Optional: If your implementation layer has additional NBAs, add them by overriding the LoadNBAForAllOpps_Ext dataflow. Then, create declare triggers to track work item updates.