[CX Enterprise Coworker] Find Where Customers Drop Off with Coworker (Funnel Investigation)

[OVERVIEW]
Four plain-language questions in Adobe CX Enterprise Coworker can show where customers drop off before purchase. In practice, you describe what you want to know, such as where people are lost on the way to purchase, and Coworker picks the funnel, runs it on your Customer Journey Analytics data view or Adobe Analytics report suite, and suggests where to look next. You do not need to know which visualization to use. Each answer leads into the next question: find the biggest drop-off, check whether marketing channel explains it, check device type, then ask what to do about it.

[IMPACT]
What you are after is where in the purchase path customers are lost and which segment accounts for it, without building a fallout visualization by hand. The output is a funnel showing drop-off at each step, channel and device breakdowns of the biggest leak, and a recommendation on what to prioritize. Adobe's worked example, which uses sample data for a fictional retailer, follows this same path. It starts at the biggest funnel leak, rules out marketing channel, and ends at mobile checkout as the main problem.

[LESSONS]
Adobe's documentation separates quick answers from deep thought work. This recipe is the second type, a multi-turn conversation where each answer shapes the next question. Describing the outcome in plain language is enough to start, and naming the dimensions, metrics, and date range, with component names exactly as they appear in your data view, gives Coworker what it needs to choose the right funnel. Adding your preferred data view to Coworker's Memory saves you from repeating it in every chat. Plan mode helps too, because Coworker can ask clarifying questions before it runs anything. Asking for recommended next steps keeps the investigation moving.

[TRYABLE]
1. In Coworker Chat, select the MCP icon in the left rail and confirm that cja-mcp is in your list of connected servers. Ask Coworker which data views you have access to and choose one.
2. Turn on plan mode.
3. Ask the opening question: Where are we losing people on the way to purchase? Use the [DATA VIEW NAME] data view for [DATE RANGE].
4. Find the largest drop-off in the funnel Coworker returns. That is your biggest leak. 5. Ask: Break that funnel down by [MARKETING CHANNEL DIMENSION]. In Adobe's example, similar drop-off rates across every channel pointed away from traffic quality as the cause.
6. Ask: Now break it down by device type. This shows whether one device accounts for the gap.
7. Ask: So what should I do? This turns the findings into a prioritized recommendation.
8. To keep going in Analysis Workspace, select Analyze in CJA next to a visualization.

[SETUP]
You need access to Adobe CX Enterprise Coworker Chat, view access to a Customer Journey Analytics data view or Adobe Analytics report suite, and Coworker connected to your analytics data (the documentation shows the cja-mcp server for Customer Journey Analytics). Your data should include the funnel events from sessions through purchase and channel and device dimensions, as in Adobe's example.

[SAMPLE_OUTPUT]
This recipe was sourced from Adobe's documentation. Full depth and context are available there, including a complete worked example: https://experienceleague.adobe.com/en/docs/cx-enterprise-ai/experience-cloud-ai/coworker/chat/use-cases/data-insights/analytics-chat