[CX Enterprise Coworker] Explore Your Analytics Data and Find the Root Cause with Coworker

[OVERVIEW]
This workflow shows how to use Adobe CX Enterprise Coworker to go from a simple question about your web analytics data to an investigated root cause in a single conversation. You skip the jumping between reports, building queries, and manually slicing data to find patterns. It starts with a broad exploration question, narrows to a trend on whatever stands out, and then asks Coworker to explain a pattern in that trend, all using Customer Journey Analytics data.

[IMPACT]
The goal is to move from a basic data question to an explained pattern without building queries by hand. The output is a visualization and table with key takeaways, a trended graph of the metric you chose, and an explanation of a recurring pattern in it. For example, in a scenario where traffic to a page shows recurring dips, the investigation could point to a repeating three-day cycle that lines up with a coordinated marketing campaign cadence, not a day-of-week effect.

[LESSONS]
Starting with a broad question gives you a lay of the land before you narrow in, and the key takeaways Coworker returns point to what is worth digging into. Coworker tells you which components it used, so you can see what data it relied on. A failed tool call does not necessarily stop the analysis, because Coworker can retry it and keep going. Coworker can also point out patterns you did not ask about, such as recurring dips in a trend, and you can then confirm that you want it to investigate. It can explain how the underlying pattern works instead of only showing a chart.

[TRYABLE]
1. Open Coworker Chat and ask a simple exploration question to get a lay of the land. For example: What are my top pages by traffic?
2. Coworker loads the Customer Journey Analytics skill, works out what you are asking, and chooses the tools and data views it needs. It returns a visualization and table with key takeaways, and tells you which components it used.
3. Read the key takeaways and pick something worth digging into. For example, if one page is driving about twice as much traffic as the next closest page, that is a strong signal worth a closer look.
4. Ask a follow-up to trend it. For example: Can you trend the views on homepage for the last month? Swap in the page or metric that stood out in your data and the time period you care about. If a tool call fails, Coworker can retry it automatically and continue.
5. Look at the trend Coworker returns and anything it points out, such as recurring dips in the data.
6. Confirm that you want Coworker to investigate the pattern, for example by asking it to check why certain days are peak versus not.
7. Coworker analyzes day-of-week patterns and looks for repeating cycles. It also pulls the marketing channels that were active on a high-traffic day and compares them with a low-traffic day.
8. Review the explanation. For example, in a scenario where the dips turn out to repeat every three days, Coworker can explain that the pattern lines up with a coordinated marketing campaign cadence and is not a day-of-week effect.

[SETUP]
To use this recipe, you need access to Adobe CX Enterprise Coworker Chat and web analytics data in Customer Journey Analytics. Coworker works out which tools and data views it needs from your question.

[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/data-insights/root-cause-analysis