ÃÛ¶¹ÊÓƵ

AI Assistant in ÃÛ¶¹ÊÓƵ Experience Platform

The following video is intended to support your understanding of AI Assistant.

Transcript
Introducing AI assistant, a natural language interface built into Experience Platform designed to enhance productivity, expand product mastery, and help users efficiently navigate enterprise data objects. But what exactly can I assistant help with? It can quickly share product knowledge, helping users learn concepts and troubleshoot, and it can provide operational insights to assist with lifecycle management, impact and value analysis. All product knowledge answers are verifiable and cited, linking to product documentation.
The suggested prompts make it easy for me to continue the conversation to get an overview of capabilities. I can head over to the discoverability panel where they are clearly outlined. Now that I know what I assistant can help with, I’ll use it to help me clean up my environment. Let’s figure out which of my audiences have never been used in journeys. Wow, that was so easy. Before, I would have had to look through all of my journey definitions to identify used audiences, and then find the remaining audiences that were not used. It would have taken me hours and this took seconds to get a list. I can see how my question was interpreted to ensure no misunderstandings. Navigate to the audience page. Review the step by step process that generated the answer, and even see the SQL that ran behind the scenes. This really helps me trust the results. Before I consider getting rid of some of the unused audiences I just uncovered. I want to see if they’re being used by other audiences. Oh well, it looks like three of them are. I’ll be sure not to delete those.
I am interested to find out what attributes are used in the in segment audience. Isn’t it nice to have all the information at your fingertips? Next, I’ll identify unused journeys. It makes it easy that I can navigate directly to journey. Optimize from the response. Last, on my hygiene journey, I’ll ask AI assistant. Best practices for deleting a schema AI assistant gives me all the information I need, including contextualizing the information for my specific sandbox.
I have learned so much from AI assistant, and I have a rich chat history that I can go back to and visit. AI assistant truly is a shortcut for getting value out of experience. Platform.

Read this document to learn about AI Assistant in ÃÛ¶¹ÊÓƵ Experience Platform.

AI Assistant in ÃÛ¶¹ÊÓƵ Experience Platform is a conversational experience that you can use to accelerate your workflows in ÃÛ¶¹ÊÓƵ applications. You can use AI Assistant to better understand product knowledge, troubleshoot problems, or search through information and find operational insights. AI Assistant supports Experience Platform, Real-Time Customer Data Platform, ÃÛ¶¹ÊÓƵ Journey Optimizer and Customer Journey Analytics.

The AI Assistant interface with the first-time user experience triggered.

IMPORTANT
You must agree to a before you can use AI Assistant. The user agreement also contains the public beta agreement. This is so that you can use additional AI Assistant features as they roll out in a beta capacity.
Select to view user agreement interface

The first page of the user agreement.

The last page of the user agreement.

Understanding AI Assistant understanding-ai-assistant

AI Assistant responds to your submitted questions by querying a database and then translating data from the database into a human-readable answer.

This internal representation of underlying data is also known as the Knowledge Graph - a comprehensive web of concepts, data, and metadata for a given answer.

The Knowledge Graph consists of sub-graphs that are referenced whenever queries submitted:

  • Customer operational insights.
  • Customer operational insights across various meta-stores.
  • Experience League documentation.

There are two classes of questions to consider before querying AI Assistant:

Product knowledge product-knowledge

Product knowledge refers to concepts and topics grounded in Experience League documentation. Product knowledge questions can be further specified into the following sub-groups:

Product knowledge
Examples
Pointed learning
  • What is the difference between an identity and a primary or foreign key?
  • What are lookalike audiences?
Open discovery
  • How can I export this dataset?
  • Are there schemas for healthcare customers?
Troubleshooting
  • Why can’t I turn on a schema owned by ÃÛ¶¹ÊÓƵ for profile?
  • Why can’t I delete a segment?

Watch the following video for additional information on AI Assistant product knowledge:

Operational insights operational-insights

IMPORTANT
Operational insights answers are in beta. Anyone that has access to the View Operational Insights permission will have access to operational insights answers.

Operational insights refer to answers AI Assistant generates about your meta data objects (attributes, audiences, dataflows, datasets, destinations, journeys, schemas, and sources), including counts, lookups, and lineage impact. It does not look at any data within the sandbox.

  • How many datasets do I have?
  • How many schema attributes have never been used?
  • Which audiences have been activated?

You can ask AI Assistant questions about your operational insights in the following domains:

Domain
Supported metadata
Unsupported metadata
Attributes
  • Attribute name search
  • Attribute - schema relationship
  • Attribute - dataset relationship
  • Attribute - audience relationship
  • Attribute - destination relationship
  • Attribute class
  • Audit
  • Deprecation status
  • Labels
  • Value stored in attributes
Audiences
  • Audience count
  • Audience type (streaming or batch)
  • Creation/modification dates
  • Activation status
  • Profile count
  • Duplicate audiences
  • Audience definition search
  • Audience - audience relationship
  • Audience - attribute relationship
  • Audience - dataset relationship
  • Audience - destination relationship
  • Name search
  • Name and ID search
  • Audience overlaps
  • Audience activation
  • Audience - campaign relationships
  • Audit
  • Create/modification
  • Labels
  • Profile qualification trends
Dataflows
  • Dataflow counts
  • Dataflow status
  • Dataflow - dataset relationship
  • Dataflow - source relationship
  • Creation/modification
  • Dataflow-batch relationships
  • Ingest profile count
Datasets
  • Dataset count
  • Profile enable status
  • Creation/modification date
  • Dataset - schema relationship
  • Dataset - audience relationship
  • Dataset - attribute relationship
  • Dataset - dataflow relationship
  • Name search
  • Name and ID search
  • Audit
  • Created by
  • Dataset - batch relationship
  • Dataset creation/modification
  • Dataset size
  • Number of profiles
  • Number of rows
  • Value search
Destinations
  • Configured destination counts
  • Destination - audience relationship
  • Destination attribute relationship
  • Account set up
  • Account credential information
  • Unique profiles activated
Journeys
  • Counts
  • Name search
  • Name and ID search
  • Journey status
  • Triggered status (audience vs. events)
  • Creation/modification dates
  • Recurring frequency
  • Attributes - journey relationships
  • Audit
  • Creation/modification
  • Created by
  • Events
  • Journey - dataset
  • Journey - schema
  • Offers
  • Profile qualification trends
  • Step events
Schemas
  • Schema counts
  • Creation/modification date
  • Schema - attribute relationship
  • Schema - dataset relationship
  • Schema - audience relationship
  • Profile enable status
  • Name search
  • Name and ID search
  • Audit
  • Creation/modification
  • Created by
  • Field groups
  • Identities
  • Identity namespaces
  • Labels
  • Number of profiles
Sources
  • Account counts
  • Account status
  • Active/inactive dataflows for each account
  • Source connector - dataflow relationship
  • Source account - dataflow relationship
  • Account credentials information
  • Account set up
  • Data ingestion metrics
  • Number of profiles
  • Source - batch relationships

For operational insights questions, answers may not reflect the current state of the UI. The data that backs these questions is updated once every 24 hours. For example, changes that users make in Real-Time CDP during the daytime are synced with the data stores at night, and then they become available for user questions in the morning. You will need to log into a sandbox to inquire about specific data related to objects.

Feature scope feature-scope

Currently, the scope of AI Assistant is as follows:

  • Product knowledge: AI Assistant can answer product knowledge questions for Experience Platform, Real-Time Customer Data Platform and ÃÛ¶¹ÊÓƵ Journey Optimizer. You can also delve into product knowledge topics for Customer Journey Analytics, but only through the Customer Journey Analytics UI.
  • Operational insights: You can ask AI Assistant with questions on operational insights on the following data objects: attributes, audiences, dataflows, datasets, destinations, journeys, schemas, and sources.

Next steps

Now that you have a general understanding of AI Assistant, you can now proceed and use AI Assistant during your workflows. Refer to the following documentation for more information:

recommendation-more-help
533e3850-1080-45ab-a426-3698091e5bb9