Best Practices for Using Captain AI
Table of Contents
Captain AI is your product coach and performance insights co-pilot. It can help you understand the impact of your Appcues experiences and boost your user engagement skills.
Capabilities
Coaching Help
- Get general guidance on best practices for improving adoption, activation, and other key outcomes in your app
- Ask for feedback on existing Experiences you've built
- General support for Appcues features
Review Experiences and other account info
- Find and list experiences by name, type, creator, status, etc.
- View experience details including steps, content, and configuration
- List segments with their targeting conditions
- View goals and their completion criteria
- Browse events tracked in the account
- List all available user properties with types
- List all available group properties
- View sample values to understand data format
Targeting and Segmentation
Describe who should see experiences and when, and Captain AI will translate those instructions into experience settings for you.
- Create new segments with targeting conditions
- View segment membership counts
For each experience, configure:
- Audience: Which users should see it
- Page targeting (web): URL patterns and domain restrictions
- Screen targeting (mobile): Screen name patterns
- Version targeting (mobile): App version requirements
- Trigger events: Custom events that launch the experience
- Frequency: Show once or every time conditions
Analytics & Reporting
Captain AI can retrieve experience performance metrics and user lists.
.png)
Account Overview
- Monthly active users (MAU)
- Total messages sent
- Tracked users count
- Flow performance summary
Experience Metrics
For any experience, the agent can report:
- Users who saw the experience
- Users who completed it
- Users who skipped or dismissed it
- Daily breakdowns over a date range
Specialized Experience Analysis
| Experience Type | Additional Metrics |
|---|---|
| Launchpads | Opens, impressions, activity breakdown |
| NPS Surveys | NPS score, promoter/neutral/detractor counts, individual responses with feedback, and sentiment analysis |
| Checklists | Per-item started/completed counts |
Goal Tracking
- Goal completion counts (total or daily)
- List of users who reached a goal
Event Analytics
- Event trigger counts
- Unique users per event
- Users who triggered a specific event
Page & Screen Views
- Most viewed pages/screens
- View counts and unique visitors
- Individual view details with timestamps
Group/Account Analytics
- Group engagement metrics (DAU, stickiness)
- List groups with properties
Output Options
Analytics can be returned as:
- Formatted text for quick reading
- CSV for export and further analysis

User Profiles
- Look up profiles by user ID and other identifier properties
- View specific properties or all available data for a given user
- See user activity history (events and page views)
- Summarize user journeys through your app and general sentiment for that user
Experience Delivery Troubleshooting
Captain AI can help diagnose common issues:
Installation Status
- Check if the web SDK is installed
- Check if mobile SDKs are installed
- View configured domains
Experience Errors
- View recent errors for an experience
- See error messages, URLs, and timestamps
- Identify targeting or content issues
Experience Management
Publish and unpublish experiences directly from Captain AI. You can also run bulk operations across all your experiences based on different filtering rules.
Build Experiences
Currently mobile flows can be build and edited within Captain AI. Just describe the purpose and general content, and the flow will be automatically generated. You can then manually edit content yourself in the builder.
Using Captain AI to answer questions about the performance of your flows, experience, goals, events or users and accounts requires sending some end user data to OpenAI, which can include User IDs or PII based on the questions asked. Your data will not be used to train any AI models. At this time, Captain AI is unable to perform analytics queries for HIPAA customers.
If you want to opt out of these Captain AI features that send end user data to OpenAI you can email support@appcues.com or Appcues admins can opt out in your Appcues account settings. For more information about how Appcues uses AI and security see our trust center FAQ on AI.
Using Captain AI
To get started, click the Captain AI nav item and ask a question in the chat window.

You can also return to and continue previous sessions:

You can quickly look up and reference experiences in your account by typing @:

Best practices
To get the most out of Captain AI, keep these tips in mind:
- Be specific in your prompts. Instead of asking “how do I improve engagement,” try “how do I improve checklist completion for trial users in their first week.”
- Please let us know if the AI Assistant’s answers are helpful or not by clicking the 👍 or 👎 icons next to the answers it provides.
- Set your business context. In your Appcues account settings, you can add details about your business (like product type, audience, or goals). Captain uses this info to provide more relevant coaching.

Prompt Ideas
These are all examples of questions we've seen customers ask; use these to discover new ways to interact with Captain AI:
Engagement Strategy
What's the best way to onboard new users who signed up but haven't completed setup?
How should I announce a new feature to power users without interrupting their workflow?
What Appcues patterns work best for reducing churn during a free trial?
I want to improve activation rates—what experiences should I prioritize?
What's the right timing and frequency for in-app messages during onboarding?
How can I re-engage users who haven't logged in for 30 days?
What's the best approach for collecting NPS feedback?
Should I use a modal, slideout, or tooltip to promote our new integration?
How do I create an onboarding flow that adapts to different user roles?
What are some proven patterns for driving feature adoption after launch?Experience Troubleshooting
Before I publish, can you help me verify my targeting rules will reach the right users?
Why is my tooltip pointing to the wrong element on the page?
Users are seeing the same announcement multiple times. How do I fix this?
My NPS survey isn't appearing even though I published it. What should I check?
The flow works in preview but not in production—what could be different?
Why are my targeting rules not matching the users I expect?
My slideout is getting cut off on mobile devices. How can I fix this?
Users say the dismiss button isn't working. What should I look at?
How do I create an onboarding flow that adapts to different user roles?
What are some proven patterns for driving feature adoption after launch?
Targeting & Segmentation
I want to target users who completed onboarding but haven't used feature X yet
How do I create a segment for trial users in their last 3 days?
Build targeting rules for enterprise customers who haven't seen our new dashboard
I need to reach users who started a workflow but didn't finish it
Create a segment for power users based on their activity patterns
How do I target users based on their subscription tier and usage?
Build rules to show a message only to users who haven't dismissed it before
I want to target new users from a specific marketing campaign
How do I exclude users who've already completed this action?
Create targeting for users who match multiple conditions across events and properties
Which of my pubished experiences are triggered by a particular event?
Do I have any experiences that are using this specific CSS selector for targeting? I’m making a change to my app’s code and want to make sure I’m not going to break any published experiences.
I have a particular flow. What other experiences is it triggered from?Analytics
Which Flow with the tag ‘Onboarding’ has the best completion rate this month?
Where are users dropping off in my signup-to-activation funnel?
Compare the performance of my two feature announcement variants.
What's the impact of my onboarding flow on 7-day retention?
Which user segment has the lowest engagement with in-app messages?
Show me the trends in NPS scores over the last quarter
What percentage of users who saw the upgrade prompt actually converted?
Which experiences have the highest dismiss rates and might need improvement?
How long does it take users to complete onboarding on average?
What's the correlation between flow completion and long-term retention?