[CX Enterprise Coworker] Assess Your Experience Platform Health and Build an Audience with Coworker
[OVERVIEW]
Adobe CX Enterprise Coworker can take you from a full operational view of your Adobe Experience Platform environment to a newly built audience in a single conversation. This is a way around the manual, time-consuming audit of how your audiences, journeys, datasets, and destinations connect. Coworker generates that view on demand, benchmarks it against an industry blueprint from Experience League, and then builds a new audience from a plain-language description, with you confirming the choices along the way.
[IMPACT]
You get your bearings in an Experience Platform environment, see where the gaps are, and act on them without writing queries. The output is a report on how audiences and journeys connect, with a health summary and recommended next steps, a benchmark showing where you are doing well and where the gaps are, and a new audience built from a plain-language description. For example, in a scenario where the report shows journeys with no audiences attached, that is a gap worth investigating, and the benchmark gives next steps for closing it.
[LESSONS]
Before you act, a broad question about how your audiences, journeys, datasets, and destinations fit together is a good way to get your bearings. Coworker can measure what it finds against an established benchmark when you point it to one, such as an industry blueprint on Experience League, which turns the report into a strategy with next steps and not only data. Before it builds anything, Coworker checks for existing audiences that might match, so you do not end up with duplicates. To choose fields, it looks at which fields are commonly used, which appear in other audiences, and which have data behind them, then asks you to confirm the ones it found. The process stays human-in-the-loop, so if a field is not right, you can tell Coworker to adjust it. If you will want the same health check regularly, you can save the conversation as a reusable skill so you do not have to retype the full prompt.
[TRYABLE]
1. Open Coworker Chat and ask for an overview of your environment. For example: I want to see a full view of my Experience Platform environment. How are my audiences, journeys, datasets, and destinations fitting together, and where are the gaps?
2. Review the report Coworker generates. It shows how audiences and journeys connect, with a health dashboard, a summary, a broader health assessment, and recommended next steps. Look for gaps worth investigating, such as journeys with no audiences attached.
3. Measure your environment against an established benchmark by naming it in your prompt. For example: Use the Retail Industry Blueprint on Experience League to show me how I'm doing against best practices. Coworker generates an artifact showing where you are doing well, where the gaps are, and clear next steps to close them.
4. Optional: if you will want this check regularly, ask Coworker to save the chat as a reusable skill with a short prompt, such as give me an overview of my system. Next time, you will not need to type out the full prompt again.
5. Move from assessment to action by describing the audience you want in plain language. For example: Create an audience of gold and platinum loyalty members who haven't purchased in six months, but have an email address on file.
6. Coworker checks for existing audiences that might match, so it does not create duplicates. If none is an exact match, confirm that you want to create the audience from scratch.
7. Coworker works out which fields to use and comes back with the fields it found, asking whether to move forward. Confirm, or tell it what to change.
8. After you confirm, Coworker builds the audience. You describe what you want in natural language and do not need to write SQL.
[SETUP]
The starting point is access to Adobe CX Enterprise Coworker Chat and an Adobe Experience Platform environment with audiences, journeys, datasets, and destinations to review. The audience creation step uses Real-Time CDP.
[SAMPLE_OUTPUT]
This recipe was sourced from Adobe's documentation. Full depth and context are available there: https://experienceleague.adobe.com/en/docs/cx-enterprise-ai/experience-cloud-ai/coworker/chat/use-cases/audiences/create-audience-from-natural-language