Beyond the first scan

Plantix is a graduation project exploring what happens after a plant is identified. A scan can name a plant or suggest a problem, but people still need to understand the result and decide what to do next.

I led a two-designer team, owning product direction, UX architecture, core flows and final design decisions. I also worked on research, prototyping, UI and testing.

Research shifted the focus to ongoing care

Interviews, a survey with 30 plant owners and a review of existing apps showed that identification only solves a brief moment. People needed to know why their plant was changing, how serious it was and which advice applied to them.

Beginners wanted a plain-language answer and a next step. Experienced owners wanted history, trends and control. I used progressive depth: a clear answer first, with detailed information available when needed.

The plant became the centre of the product

Card sorting with 12 participants showed that people grouped features around tasks rather than technology. A saved plant profile became the link between identification, diagnoses, observations, care history, upcoming tasks and optional sensor data.

The core journey became: scan, understand, save, care, monitor and reassess. This connected the first useful answer to a reason to return.

AI results with room for uncertainty

Identification starts with a photo or gallery image and simple guidance for capturing a useful shot. The result shows the likely match. When confidence is lower, people can review alternatives, retry the photo or refine the result.

Diagnosis needs more than a photo

A damaged leaf does not explain its own cause. I combined photos with short questions about symptoms and recent care. The flow asks only for context that helps narrow the result, and offers recovery options when confidence is low.

Care that builds on a plant’s history

A saved plant collects observations, diagnoses, completed actions and environmental changes. The collection highlights plants that need attention, while detailed profiles show trends in light, temperature, humidity and soil conditions.

Reminders belong to the plant and respond to its context. Notifications lead directly to an action, and completed or missed tasks become part of its history. Sensors and advanced tools remain a secondary layer for people who want more control.

Testing made the product smaller

Eight target users completed the main prototype flows without guidance. Testing exposed confusing terminology, dense screens and complicated sensor setup. I simplified the copy, adjusted the hierarchy and split setup into smaller steps.

I also removed a separate knowledge library. People wanted relevant advice where they were already making a decision, so educational content moved into identification, diagnosis and care.

A focused concept, with a clear MVP

The result is a high-fidelity interactive prototype covering the journey from first scan to ongoing care. For a first release, I would focus on identification and diagnosis, saved plants, care guidance, monitoring and reminders. Sensors, deeper analytics and specialist tools would follow after validating that core behaviour.

I explored freemium, subscriptions, partnerships and B2B use as product scenarios. These are hypotheses, not launch results or business metrics.

What I took from the project

The hardest UX work surrounded the AI: getting useful input, explaining uncertainty and helping people act on the result. Recognition can create first-use value; history, care and monitoring can make the product useful again tomorrow.

Leading another designer also meant keeping the product coherent while splitting tasks, reviewing decisions and staying responsible for the core flows.