I designed a proactive AI agent to help maintain accurate and trustworthy journey maps on a SaaS Platform
I designed a proactive AI agent to help maintain accurate and trustworthy journey maps on a SaaS Platform
I designed a proactive AI agent to help maintain accurate and trustworthy journey maps on a SaaS Platform
*NDA Notice
Confidential and proprietary details have been removed or anonymized to protect client information.
*NDA Notice
Confidential and proprietary details have been removed or anonymized to protect client information.
The Dish in One Bite
The Dish in One Bite
Project Overview
Project Overview
Problem Space
Problem Space
Keep journey maps accurate and up-to-date with less manual effort
Keep journey maps accurate and up-to-date with less manual effort
Business Goal
Business Goal
Increase platform long-term value and user trust by ensuring the journey maps stay accurate and up-to-date
Increase platform long-term value and user trust by ensuring the journey maps stay accurate and up-to-date
Outcome
Outcome
Reduce manual effort and enable more reliable journey map maintenance with AI
Reduce manual effort and enable more reliable journey map maintenance with AI
Customer journey maps are meant to guide business decisions, but they often become outdated as customer behaviors, products, and data evolve. While the current platform, a journey mapping software, already supports journey creation with AI, analytics integration, and AI-assisted insights, maintaining journey maps still relies heavily on manual reviews and disconnected signals.
In this project, my team and I explore how an agentic AI maintenance system could help organizations keep journey maps accurate, trustworthy, and actionable over time. Our solution is a system that can proactively detect potentially outdated content, map data changes back to specific journey steps, and surface evidence-based suggestions for users to review and apply.
Beyond improving maintenance workflow for users, this solution also creates an opportunity for the business to strengthen trust in journey maps as living tools rather than static documentation. By making customer insights more reliable, scalable, and easier to maintain, the platform can provide greater long-term value for enterprise teams managing complex customer experiences.
Customer journey maps are meant to guide business decisions, but they often become outdated as customer behaviors, products, and data evolve. While the current platform, a journey mapping software, already supports journey creation with AI, analytics integration, and AI-assisted insights, maintaining journey maps still relies heavily on manual reviews and disconnected signals.
In this project, my team and I explore how an agentic AI maintenance system could help organizations keep journey maps accurate, trustworthy, and actionable over time. Our solution is a system that can proactively detect potentially outdated content, map data changes back to specific journey steps, and surface evidence-based suggestions for users to review and apply.
Beyond improving maintenance workflow for users, this solution also creates an opportunity for the business to strengthen trust in journey maps as living tools rather than static documentation. By making customer insights more reliable, scalable, and easier to maintain, the platform can provide greater long-term value for enterprise teams managing complex customer experiences.
Ingredients for this Project
Ingredients for this Project
Timeline
Timeline
Jan 2026 - May 2026
Jan 2026 - May 2026
My Role
My Role
UX Designer
UX Designer
Responsibility
Responsibility
UX research
Literature Review
Sketching
Interaction Design
Usability Testing
Design Iteration
UX research
Literature Review
Sketching
Interaction Design
Usability Testing
Design Iteration
Tool
Tool
Figjam
Figma Board
Maze
Figjam
Figma Board
Maze
My Key Contribution
My Key Contribution
Led Hi-Fi Prototyping & Built a Component System from Scratch
Created the Testing Protocol, Conducted Research & Synthesized Findings
Helped Coordinate Project Planning & Team Scheduling
User Persona
User Persona
Preparation
Preparation
What I Did Before Finding Solutions
What I Did Before Finding Solutions
Click it
Cooking
Cooking
Getting the Solution
Getting the Solution
Final Dishes
The final design solution introduces an AI maintenance agent that helps teams keep customer journey maps accurate and up to date over time. Instead of relying on manual reviews and scattered signals, the system proactively surfaces suggested updates, explains the reasoning behind them with supporting evidence, and guides users through the review and application of changes. To balance automation with trust and control, the experience combines proactive AI suggestions with reactive conversational assistance, allowing users to explore, verify, approve, deny, or revisit recommendations directly within their workflow.
Here is the logical flowchart of our final solution for communication and teamwork purposes.
The final design solution introduces an AI maintenance agent that helps teams keep customer journey maps accurate and up to date over time. Instead of relying on manual reviews and scattered signals, the system proactively surfaces suggested updates, explains the reasoning behind them with supporting evidence, and guides users through the review and application of changes. To balance automation with trust and control, the experience combines proactive AI suggestions with reactive conversational assistance, allowing users to explore, verify, approve, deny, or revisit recommendations directly within their workflow.
Here is the logical flowchart of our final solution for communication and teamwork purposes.
1. Proactive AI Suggestions
The AI maintenance agent proactively monitors journey data and surfaces suggested updates when information may be outdated, inconsistent, or missing.
The AI maintenance agent proactively monitors journey data and surfaces suggested updates when information may be outdated, inconsistent, or missing.
Evidence-Backed Suggestions
Each suggestion includes supporting evidence and contextual reasoning to explain why the AI recommended the change. Users can review related insights and source documents to manually verify the suggestion before taking action.
Each suggestion includes supporting evidence and contextual reasoning to explain why the AI recommended the change. Users can review related insights and source documents to manually verify the suggestion before taking action.
Contextual AI Assistance
Users can ask the AI follow-up questions about specific suggestions to get additional context, explanations, or clarification directly within their workflow.
Users can ask the AI follow-up questions about specific suggestions to get additional context, explanations, or clarification directly within their workflow.
Human-Controlled Decision Making
The system keeps users in control by allowing them to approve, deny, or skip AI-generated suggestions rather than automatically applying changes. This helps balance automation with trust and human oversight. Suggested areas are highlighted directly within the journey map to help users quickly identify where attention is needed.
The system keeps users in control by allowing them to approve, deny, or skip AI-generated suggestions rather than automatically applying changes. This helps balance automation with trust and human oversight. Suggested areas are highlighted directly within the journey map to help users quickly identify where attention is needed.
Suggestion History & Undo Actions
Users can revisit previously approved or denied suggestions via a history view that tracks past actions. This also allows users to review context and undo decisions when needed.
Users can revisit previously approved or denied suggestions via a history view that tracks past actions. This also allows users to review context and undo decisions when needed.
Leftover and Lesson
Leftover and Lesson
What I learned
What I learned
Communicating Ideas More Clearly Across Teams
Creating Better Collaboration Frameworks
Building Scalable Hi-Fi Prototypes
Designing with Business Goals in Mind
What I would do with more time
What I would do with more time
Conduct More Usability & Contextual Testing
Design an Onboarding Experience for this AI Feature
Revisit AI Support for High-Security Organizations
Let's connect!
You're interested in what I did? How about a coffee chat?
