Helping mental health patients and remember reflect on their therapy sessions using AI

Helping mental health patients and remember reflect on their therapy sessions using AI

Helping mental health patients and remember reflect on their therapy sessions using AI

Role

Research, UX/UI Design, Product Strategy, Prompt Engineering, Testing Conversational AI

Senior Product Designer,

Mobile and Web

Team

Head of Product, Head of Design, Head of AI, CTO, Chief Clinical Officer, Senior PM, Front and backend Developers

We were asking patients for too much effort upfront

We were asking patients for too much effort upfront

We were asking patients for too much effort upfront

HelloSelf is a teletherapy startup connecting mental health patients with therapists. In early 2024, the team prepared to create and introduce its first AI-powered experience to patients. However, we hit a roadblock: we realised our plan—to start the conversational AI around goal tracking—meant patients had to continuously “feed” and "update" it with personal data. And without patients having used the AI before, the plan felt too much of an ask.

Opportunity

How can we… introduce AI in a way that feels natural, low-effort, useful, and aligned with their therapy?

So, how can we…
design an inclusive experience for Buddhists with mobility-impairment?

XX% of all sessions every week use our AI

Business Impact?

???

Business Impact?

???

Business Impact?

???

Business Impact?

???

Business Impact?

???

Positive Qual-Feedback

???

Positive Qual-Feedback

???

Positive Qual-Feedback

???

Positive Qual-Feedback

???

Positive Qual-Feedback

???

Positive Quant-Feedback

???

Positive Quant-Feedback

???

Positive Quant-Feedback

???

Positive Quant-Feedback

???

Positive Quant-Feedback

???

0-to-1 Designs on Mobile and Web

0-to-1 Designs on Mobile and Web

0-to-1 Designs on Mobile and Web

Desired outcome:

Introduce patients to AI… at a moment that feels natural—so it’s low-effort, genuinely useful, and becomes part of their therapy routine.

So, how can we…
design an inclusive experience for Buddhists with mobility-impairment?

Revised Product Roadmap

Revised Product Roadmap

Worked with the team to pivot the AI to start:

…from goals, where the user has to bring context to the AI [OLD] ❌
…to session summaries, where rich context already exists [NEW] ✅


New AI-Ready Call Station

New AI-Ready Call Station

I redesigned the UX/UI of the call station so patients could consent-to/activate AI features alongside their therapist—making the experience clear, collaborative, and non-disruptive.

I redesigned the UX/UI of the call station so patients could consent-to/activate AI features alongside their therapist—making the experience clear, collaborative, and non-disruptive.

AI-generated Summary

AI-generated Summary

I designed the UX/UI for reviewing session summaries to support memory recall—making the experience simple and easy to return to.

Conversational AI

Conversational AI

I designed the UX/UI for how patients chat with the conversational AI to reflect on their sessions. I also added a feedback mechanism to help the team improve model responses over time—making the experience feel human and safe to use.

Testing Conversational AI

Testing Conversational AI

Working with Head of AI and Chief Clinical Officer, I helped test and evaluate the quality of AI-conversations based on different synthetic personas I generated.