Coaching App
Turning AI Chat
into Meaningful
Coaching
The main premium feature failed to deliver value.
In addition to providing daily motivational videos and audio clips, PepTalk has developed an AI feature that lets users chat with their favorite personalities: PepCoach.
If the PepCoach feature initially felt avant-garde, users quickly found it underwhelming compared to what they expected from an AI-powered coaching experience.
UX/UI Analysis
When it was launched, the promise of chatting with a AI agent acting like your favorite celebrity was quite attractive. But the feature quickly revealed its limits: users were interacting with a standard, outdated AI agent overlaid with a language filter, unable to offer any valuable content... when the app is actually packed with rich content.
-
Low added value The AI responses were generic and not insightful.
-
Disconnected from the product The feature didn't leverage the app's core content: audios, videos, and quotes.
-
Weak positioning The "celebrity coach" concept created expectations the product couldn't meet.
The real value isn't the AI itself.
It's the relevance of the interactions it can bring up.
Four decisions that shape the experience
Structure free input toward relevant themes.
Ground every response in audios, videos, and quotes.
Turn "Personalities" into an enhancement, not the core.
An outdated design doesn't do justice to a technically advanced feature.
Reframe Pep Coach as a guided, content-driven experience.
New flow:
Constraints & design implications
- AI model undecided The UI abstracts the API call entirely. Content triggers work regardless of which model ships.
- No streaming in v1 Coaching responses are pre-authored scripts injected at defined conversation triggers, not raw model output.
Default to a generic coach
Users now start with a neutral AI Coach. The celebrity framing was over-promising. Users expected a real personality, not a renamed model. Making the AI Coach the default removes that mismatch and lets content quality carry the experience.
- Celebrities are optional, not the entry point.
- This removes the pressure of choosing a personality before the experience begins.
Guide conversations with topics
Instead of open-ended chat, users start from a predefined coaching topic. A blank input works for curiosity-driven users, but PepTalk's audience often comes with an emotional need they can't easily articulate. Topics give them a starting point and reduce the gap between "I feel stuck" and actually receiving useful coaching.
- Topics ground the conversation in the user's actual needs.
- They help the AI provide more relevant and actionable responses.
Structure free input subtly
When users type freely, the AI detects the underlying topic automatically. Forcing everyone through topic selection would have felt patronizing for returning users. Keeping free input but classifying it silently gives both segments what they need without branching the flow.
- Users feel free to express themselves naturally.
- The system maps their input to the right coaching category.
Inject content into conversations
The AI surfaces relevant videos and audio from the app directly in chat. PepTalk's real competitive advantage is its content library, not its AI model. Keeping content and chat separate meant users engaged with one or the other. Injecting content into responses is what makes the AI feel distinctly PepTalk rather than a generic chatbot.
- Content recommendations feel organic and timely.
- The feature finally connects the AI to the rest of the product.
Introduce dynamic coaching
Coaching adapts in real time based on what the user shares. Static responses train users not to engage deeply, as they quickly learn the system doesn't respond to nuance. Adaptive tone is what creates the "this actually listens" feeling that drives return sessions.
- The AI adjusts its tone and suggestions based on the conversation.
- Users feel heard and understood, not just answered.
Make it look premium
A modernized UI that signals quality and justifies the premium tier. The old design looked like a side project, creating a mismatch between the perceived value of "personal AI coach" and the visual quality users associate with that price point.
- Visual refinements elevate the perceived value of the feature.
- The new design is consistent with the overall app aesthetic.
A content-driven coaching experience
The new design reduces friction by guiding users toward specific, actionable conversations.
They are now encouraged to pick a topic, making it easier to get structured advice and relevant content right away.
This way, the feature becomes a practical daily coach, not just a chatbot.
- Topic selection frames every conversation from the start
- App content injected contextually into coaching responses
- Premium visual redesign reinforces the quality of the advice
Results
Upgrade rate among active users improved as the AI-powered suggestions surfaced the paywall at more relevant, high-intent moments.
Users returning to the AI coach in subsequent sessions, driven by more contextual and actionable responses that rewarded re-engagement.
Projected increase in long-term value, modelled from improved conversion and retention rates post-launch.
What I'd improve next
The redesign improved conversion and return rate, but the experience still has meaningful gaps once users are inside. These are the improvements most likely to compound on the current gains.
The goal wasn't to build a smarter AI.
It was to make the AI feel useful.
