AI Assistant UI Guide

Read this guide to learn how you can use AI Assistant in the Adobe Experience Platform UI.

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.

Access AI Assistant in the Experience Platform UI

To launch AI Assistant, select the AI Assistant icon from the top header of the Experience Platform UI.

The Experience Platform home page, with the AI Assistant icon selected and the AI Assistant interface open.

The AI Assistant interface appears, immediately providing you with information to get started. You can use the options provided under Ideas to get started to answer questions and commands such as:

  • Which of my audiences are activated?
  • What is a schema?
  • Tell me some common use cases for Real-Time CDP

AI Assistant UI guide

NOTE
The following workflow is an example that uses the experience event schema creation process to illustrate how you can use AI Assistant when using the Experience Platform UI.

Consider a use case in which you are creating a Device Trade in Event Schema. During the experience event schema creation process, you come across the eventType field. “At this point, you have the option to either exit your workflow and refer to the basics of a schema composition documentation, or you can use AI Assistant to retrieve answers to your questions and find additional resources through the documentation links recommended by AI Assistant.”

To begin, enter your question in the text box provided. In the example below, AI Assistant is provided the question: “What is the eventType field in an ExperienceEvent schema?

AI Assistant for Experience Platform with the following question prepared for querying: "What is the eventType field in an ExperienceEvent schema?

AI Assistant then queries its knowledge base and computes an answer. After a few moments, AI Assistant returns an answer and related suggestions that you can use as follow up prompts.

AI Assistant for Experience Platform with an answer to the previous query.

After receiving a response from AI Assistant, you can select from a number of options to decide how you want to proceed.

AI Assistant features features

This section outlines the different features of AI Assistant that you can use during your workflows on Experience Platform.

View operational data objects view-operational-data-objects

Depending on your query, AI Assistant provides additional information pertaining to the data in your sandbox. To view how the response to your query applies to your particular sandbox, select In your sandbox.

When viewing data pertaining to your sandbox, AI Assistant may provide direct links to specific UI pages that display your queried data.

Select to view example

In this example, AI Assistant returns additional information regarding the existing XDM schemas in your sandbox, including their total count and the five most commonly used fields.

The "in your sandbox" dropdown window open, displaying additional information on your schemas.

View citations view-citations

You can verify responses returned to you by AI Assistant by reviewing citations available with every product knowledge answer.

Select to view an example of how to display sources

To view citations and validate AI Assistant’s response, select Show sources.

The AI Assistant response with "Show sources" selected.

AI Assistant updates the interface and provides you with links to documentation that corroborate the initial response. Additionally, when citations are enabled, AI Assistant updates the response to include footnotes to indicate the specific parts of the answer that reference the provided documentation.

A dropdown menu of the citations that AI Assistant provides for concept questions.

You can also use the suggestions that AI Assistant provides under Related suggestions to further explore topics related to your original question.

A list of suggestions provided by AI Assistant.

Operational insights operational-insights

You must be in an active sandbox in order for AI Assistant to sufficiently respond to a question about your operational insights.

Select to view an example of an operational insights question

In the example below, AI Assistant is asked the following query: “Show me dataflows that were created using the Amazon S3 source”.

A question about operational insights.

AI Assistant then responds with a table listing your dataflows and their corresponding IDs. To view the whole table of data, select the expand icon on the top right.

An operational insights answer

An expanded view of the table appears, providing you with a more comprehensive list of dataflows based on the parameters of your query.

A view of the expanded table.

When prompted with an operational insights question, AI Assistant provides an explanation of how it computed the answer. In the example below, AI Assistant outlines the steps it took in order to identify the dataflows that were created using the Amazon S3 source.

AI Assistant providing an explanation on how it computed its answer.

You can also provide filters and modifications to your questions, and you can instruct AI Assistant to render its findings based on the filters that you include. For example, you can ask AI Assistant to show you a trend of the count of segment definitions in the order of their created date, remove segment definitions with zero total profiles, and use month names instead of integers when displaying the data.

Note: Operational insights answers are currently in beta. Select the tooltip icon in the AI Assistant user interface to view the Beta notice and for a link to the documentation.

AI Assistant tooltip icon selected.

Verify operational insights responses verify-responses

You can verify each response related to operational insights questions using an SQL query that AI Assistant provides.

Select to view example of verifying operational insights responses

After receiving an answer for an operational insights question, select Show sources and then select View source query.

view source query

When queried with an operational insights question, AI Assistant provides an SQL query that you can use to verify the process that it took to compute its answer. This source query is for verification purposes only and is not supported on Query Service.

example of source query

Use auto-complete use-auto-complete

You can use the autocomplete function to receive a list of data objects that exist in your sandbox. Autocomplete recommendations are available for the following domains: audiences, schemas, datasets, sources, and destinations.

Select to view an example of auto-complete

You can use autocomplete by including the plus symbol (+) in your query. As an alternative, you can also select the plus sign (+) located at the bottom of the text input box. A window appears with a list of recommended data objects from your sandbox.

Example of auto-complete

Use multi-turn use-multi-turn

You can use AI Assistant’s multi-turn capabilities to have a more natural conversation during your experience. AI Assistant is able to answer follow-up questions, given. that context can be inferred from an earlier interaction.

Select to view an example of multi-turn

In the example below, AI Assistant is first asked for the total number of dataflows and then is asked to list the 10 most recent dataflows.

Example of multi-turn

Start a new conversation

You can change topics with AI Assistant by resetting and starting a new conversation.

Select to view an example of resetting your conversation

To reset, select the ellipses (...) on the AI Assistant interface and then select Start new conversation. This informs AI Assistant that you intend on changing topics and can be particularly helpful when troubleshooting queries that are either failing or referencing incorrect information.

The ellipses selected and the start new conversation option selected.

Use discoverability use-discoverability

You can use AI Assistant’s discoverability feature to view a list of the general subjects, grouped into entities, that AI Assistant supports.

Select to view example of discoverability

To view discoverability, select the lightbulb icon on the top header of the AI Assistant interface.

The AI Assistant discoverability feature.

Next, select a category and then select a prompt from the list provided. You can use this feature to get a better idea of the types of questions that AI Assistant can answer. You can also update the pre-existing prompts with specific details that pertain to your sandbox using free text or autocomplete.

The AI Assistant prompts in discoverability.

Provide feedback feedback

You can provide feedback of your experience with AI Assistant using the options provided with answer.

To provide feedback, select either thumbs up, thumbs down, or a flag after receiving a response from the AI Assistant, and then input your feedback in the provided text box.

The feedback option in AI Assistant.

Select to view more examples
tabs
Thumbs up

Select the thumbs up icon to provide feedback on what went well with your experience with the AI Assistant.

The positive feedback window.

Thumbs down

Select the thumbs down icon to provide feedback on what could be improved upon based on your experience with the AI Assistant. During this step, you can also provide specific comments regarding your experience. Feedback provided in the comments is reviewed daily.

The negative feedback window.

Flag

Select the flag icon to provide further reports on your experience using the AI Assistant.

The report results window.

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