Analyze Customer Journey Analytics data with Coworker Chat
Adobe CX Enterprise Coworker Chat can perform advanced data analysis that was previously possible only in Analysis Workspace. Coworker Chat accesses data from your Customer Journey Analytics data views, allowing you to explore that data and get answers to natural-language prompts.
Before you begin your analysis, learn about the Coworker Chat interface and configuration options, then make sure Coworker is connected to Customer Journey Analytics and to the data view that contains the data you want to use.
Get started with Coworker Chat
Interface and configuration options
Before you use Coworker Chat with your Customer Journey Analytics data, learn how to sign in and manage configuration options for the following features:
-
Chat inputs
-
Conversations
-
Marketplaces
-
MCP servers
-
Memory
-
Plugins
-
Skills
-
And more
For more information, see the Coworker Chat UI guide.
Use cases for Customer Journey Analytics
You can see Customer Journey Analytics use cases and sample prompts that practitioners are using in Adobe CX Enterprise Coworker Chat. Each prompt is built to be copied, adapted with your own data and context, and refined through conversation.
For more information, see Use cases.
Verify that Coworker Chat is connected to Customer Journey Analytics
-
In Coworker Chat, verify that Coworker is connected to Customer Journey Analytics:
-
Select the MCP icon in the left rail, then make sure that cja-mcp is available in your list of connected MCP servers.
-
(Conditional) If cja-mcp is not yet connected, select Add MCP Server, specify cja in the Server Name field and select it when it appears, then select Add Server.
Connect to the right data view
A data view is a container in Customer Journey Analytics that determines how data is interpreted.
You might have access to various data views in Customer Journey Analytics, each containing different dimensions and metrics that Coworker can use when analyzing data.
Decide which data views you want to use
Tell Coworker the types of questions you want answered, and ask it which data views you have access to that would be best to provide that information. You can also set your data view as a preference in memory.
You:
I’m interested in learning where customers drop off in the customer journey. Which data views in Customer Journey Analytics do I have access to that would be able to answer this question for me?
Coworker Chat response:
You have access to three data views. The Customer lifecycle data view contains the following dimensions and metrics, which would be best for answering your question.
You:
Great, let’s use that data view.
Coworker Chat response:
Okay, I’ll use the Customer lifecycle data view to answer future questions in this chat session.
Add a data view preference in Memory
Coworker Chat contains a memory feature that allows you to provide it with access to information that spans across all chats. It’s a good practice to add your prefered data views as preferences in Coworker’s memory.
-
In Coworker Chat, in the left nav, select the Memory icon.
-
On the Memory page, in the Stored preferences section, specify one or more data views that you want Coworker Chat to use in your chats.
Analyze in Customer Journey Analytics
After Coworker creates a visualization, you can open the visualization in Analysis Workspace in Customer Journey Analytics for deeper analysis with more granular control. The visualization opens in a new Analysis Workspace project in Customer Journey Analytics.
To open a visualization in new Analysis Workspace project:
-
Select Analyze in CJA next to any visualization that is created in Coworker.
-
With the visualization open in Customer Journey Analytics, you can use the Analysis Workspace drag-and-drop browser interface to make modifications, further craft your analysis, create an audience, and much more. You can even share your Workspace project with anyone you choose.
For more information about Analysis Workspace, see Analysis Workspace overview.
Example: Find where customers drop off
You can ask Coworker Chat to use your data to analyze any business question.
For example, as a marketing manager, merchandiser, or growth lead, you might want to understand where customers abandon the path to purchase, why they did, and what can be done to drive higher conversion rates.
The types of questions you can ask
You don’t need to know what a “fallout visualization” is, or which metric goes in which slot. Instead, describe the outcome you care about in plain language:
- “Where are we losing people on the way to purchase?”
- “What’s my full conversion funnel, from product view to checkout?”
- “Which marketing channels leak the most between cart and purchase?”
- “Is cart abandonment worse on mobile or desktop?”
- “Do people from paid social convert differently than people from email?”
The conversation
1. Start with the business question
You:
Where are we losing people on the way to purchase?
Coworker Chat response:
Notice that Coworker Chat chooses the right visualization, sequences the touchpoints, and even adds recommended next steps.
This is a funnel question — let me run the conversion funnel to see where drop-off happens on the path to purchase.
Here’s where you’re losing people:
The big finding: cart to purchase is your biggest leak
28,463 people add items to their cart but never complete the purchase. That’s an 83.6% cart-to-purchase drop-off rate — by far the largest single point of failure.
To put it in dollar terms, converting just 10% more of those cart-adders would add about 2,846 purchases. At the current data scale, that’s potentially significant revenue left on the table.
What this tells you about priorities:
Recommended next steps:
- Break down cart abandonment by marketing channel — are certain channels bringing low-intent traffic that adds to cart but never buys?
- Look at cart abandonment by device type — is mobile checkout friction killing conversions?
- Identify which products get abandoned most — pricing issue? Shipping surprise?
Which of these would you like me to dig into next? The channel breakdown would tell you directly which marketing actions are bringing you “almost-buyers” versus actual buyers.
2. Drill into the leak
You:
Okay, let’s break down by marketing channel
Coworker Chat response:
There’s a custom Marketing Channel dimension. Let me pull the funnel by that, then calculate the per-channel conversion rates and identify where each channel leaks.
The verdict: the leak is not channel-specific
This is a really revealing finding. Here’s the per-channel funnel breakdown:
Key takeaways:
- The cart-to-purchase drop-off is uniformly bad across all channels (83-84%). This means the problem isn’t about traffic quality — every channel delivers similarly engaged visitors. The leak is in your checkout experience itself, not your marketing.
- No channel is significantly better or worse at converting. Overall conversion rates cluster tightly between 3.8% and 4.2%, and revenue per session is nearly identical ($495-$512).
- Where the volume impact matters most: paid search loses the most people in absolute terms (9,015 cart abandonments), followed by organic search (6,449 lost). These are the biggest dollar-value opportunities because they drive the most traffic.
What this tells you strategically
The marketing channels are doing their job — they’re all getting people interested and adding to cart at similar rates. The problem is downstream of marketing: your checkout and payment flow is where the money is leaking.
Recommended next investigations:
- Break down cart abandonment by device type — is mobile checkout broken or frustrating?
- Look at which products get abandoned most — is there a pricing or shipping surprise at checkout?
- Check if the “holiday_flash_sale” campaign had better checkout conversion — urgency-driven campaigns might overcome checkout friction
Which angle would you like to explore next?
3. Keep investigating
You:
Interesting. Let’s trying breaking down by device type.
Coworker Chat response:
Found it: mobile checkout is broken
The funnel is identical across devices until checkout — then mobile falls off a cliff:
The smoking gun
The browsing and add-to-cart experience is fine on mobile (identical ~45% browse rate, ~55% add-to-cart rate). People are equally interested and engaged. But something in the mobile checkout flow is killing conversions.
The revenue opportunity
If mobile checkout converted at the same rate as desktop, you’d gain ~1,991 additional purchases — a 35% increase in total purchase volume from fixing one experience.
What’s likely happening
The data pattern (equal engagement, catastrophic checkout drop) is a classic signal for:
- Payment form friction on small screens (autofill issues, form layout)
- Unexpected costs revealed at checkout (shipping, tax) causing sticker shock
- Guest checkout not available or a login wall on mobile
- Page load or timeout issues during payment processing on mobile
Recommended next steps:
- Break down mobile cart abandonment by product category — is it worse for high-price items (suggesting mobile payment trust issues)?
- Look at which marketing channels drive the most mobile traffic — are you spending paid media dollars to send people into a broken mobile funnel?
- Check if there’s a page or site-section signal — can we see which checkout pages mobile users hit last before abandoning?
Which would you like to explore, or is this enough evidence to take to your UX and checkout team?
4. Turn it into a decision
You:
So what should I do?
Coworker Chat response:
Based on what the data shows, here’s where I’d focus:
- Fix the mobile checkout — it’s not a channel problem. Every channel is converting people into the cart at a similar, healthy rate, so the ad spend is working across the board. The revenue is being lost specifically in the mobile checkout flow, which is where the fix belongs.
- Start with payment and form friction. These are the most common reasons high-intent mobile shoppers abandon a cart. Offering mobile wallet options and shortening the form are usually the fastest wins.
- Re-check after the fix. Once checkout changes ship, watch whether mobile’s cart-to-purchase rate moves toward the desktop rate of 23.2%.
Want me to save this as a project so you can track it, or set an alert if mobile cart-to-purchase drops below a threshold?
What just happened
In four plain-language questions, Coworker helped us:
- Build a multi-step conversion funnel and flag cart-to-purchase as the biggest leak
- Rule out marketing channel as the cause — every channel leaked at nearly the same rate
- Isolate the real problem to mobile checkout, and quantify the fix at a 35% lift in purchases
- Walk away with a specific fix to prioritize: mobile payment and form friction. This is benchmarked against desktop’s 23.2% conversion rate