Customer Success · 2024
AI Customer Success Agent
The Customer Success team was handling repetitive support tickets instead of focusing on strategic work. I designed an AI agent that solved both problems: clients got fast, automatic answers to their questions, and the team got their time back for high-impact work.
The Customer Success team was overwhelmed by repetitive support tickets, answering the same questions over and over instead of focusing on retention and expansion. Meanwhile, users wanted answers right away. They ignored the documentation because it was not easy to find what they needed. So we asked ourselves:
How might we deliver instant, accurate answers to users without overloading the Customer Success team or building documentation nobody reads?
Response Time
Reduction achieved
48h → 5min
Queries Resolved
Instantly by AI
50%
User Satisfaction
Maintained throughout
≥80%
Competitive Analysis
Analyzed AI agents across platforms to identify proven interaction patterns.
Core Principle
Users need speed and control, not advanced AI. Pulse suggests, never dictates, and has a clear escalation path when AI cannot answer.
AI Behavioral Design
Defined Pulse's 5 core capabilities and failure protocols.
Placement Strategy
Positioned in the top support menu: visible when needed, unobtrusive when not.
Interaction Model
Single input field with smart prompts. Natural, fast, and uncluttered.
Key trade-off
- ·AI scope had to be bounded. Not a ChatGPT-style open conversation.
- ·Design system limitations. Instead of the expected fixed floating button, we had to find a new placement that felt intuitive and did not block the information on the boards.
KI 1:The goal was efficiency, not innovation theater. Users prioritized speed over sophistication, and simple, fast answers outperformed impressive AI capabilities.
KI 2:Control builds trust. Keeping users in charge of every interaction (Pulse suggests, users decide) maintained high satisfaction even when AI could not answer.
KI 3:Bounded AI succeeds where open-ended fails. Defining clear capabilities and graceful failure paths created reliable value instead of unpredictable experiences.
This project taught me that AI works best when users stay in control and the AI has clear limits. The 1-month timeline forced me to focus on what mattered most: workflows that help people right away, not building every possible feature.
Next time, I'd start with a smaller group of users first to catch problems early, then improve the AI based on how people actually use it.
Continue exploring
