All work

Preserving a life story — and a voice the family can still talk to — Valinor case study

Valinor helps people preserve their legacy. An AI interviewer asks about their life and follows up on every answer; the stories become a storybook with photos and recordings, and a digital twin their children and grandchildren can chat with for years to come. I designed it end to end — the web app, the gifting flow and the admin panel.

Client
Valinor — “Connect to Future”
Role
Lead Product Designer — end to end
Company
Biz4Group LLC
Timeline
2022 – 2024
Platform
Web app + admin panel
Valinor — product screens
+30%User engagement after the redesign
150People aged 60+ surveyed before design
15Core interview questions, plus themed sets
3Products: app, gifting and admin
01 Context

Stories that usually disappear

What Valinor is

Valinor is an AI legacy platform. Instead of writing a memoir, people simply talk: an AI interviewer asks about their life, follows up on what they say and turns the answers into a storybook. Those same stories power a digital twin — a chatbot their family can ask anything, in their voice and style.

Who it’s for

Two people, often decades apart. The storyteller — usually 60+ and not always comfortable with technology — and the family: children who often buy Valinor as a gift for a parent, and grandchildren who may be too young to listen today but will want those stories later.

The interview — a parent question, an AI follow-up, and the choice to answer by voice or text.
02 Starting point

A generation gap, not a lack of stories

People want to pass on their history and what life taught them. Their grandchildren are often too young to take it in — and by the time they are ready, it may be too late to ask.

The problem

Too young to listen

Young grandchildren can’t yet appreciate the stories their grandparents most want to share.

The problem

Writing is hard work

Long writing sessions are tiring and, for many older adults, physically painful — so stories never get written down.

The problem

Where do I start?

The biggest barrier wasn’t technology. It was not knowing what to share or how to structure a life story.

Market gap

One-way products

Existing tools turn answers into a printed book or a family tree. None let a family actually talk with those memories.

Opportunity

An AI that asks

A conversational AI can do what a curious grandchild would: ask, follow up and keep the story going.

Opportunity

A gift, not a chore

Adult children want their parents’ stories kept. Making Valinor something you can give turned a hard ask into a present.

How the work ran

  1. Research

    Survey and card sorting

    An online survey of 150 people aged 60+, then an open card sort of 30 life topics with older participants.

  2. Define

    Persona and market

    A primary persona grounded in the findings, plus a teardown of StoryWorth and Ancestry.

  3. Explore

    Sketch both journeys

    Four concepts for recording and three for the family chat — tested and narrowed down in a two-month first design phase.

  4. Design

    The app, gifting and admin

    The interview, storybook, digital twin and sharing; gift subscriptions and plans; and the admin panel that runs it all.

  5. Grow

    Redesign and results

    Iterated on the core experience with real use — and lifted engagement by 30%.

03 Research & insights

Listening to the people who hold the stories

It was the company’s first AI product, so we didn’t guess. We asked older adults directly how they feel about technology, storytelling and talking to an AI.

Methods

  • Online survey of 150 people aged 60+
  • Open card sorting with 30 life-topic cards
  • Primary persona from the findings
  • Competitive analysis: StoryWorth and Ancestry
  • Concept testing on early sketches

Key insights

  1. Speaking beats writing

    Most people preferred to tell their stories out loud. Writing was slow, tiring and for some physically painful — voice had to come first.

  2. Prompts remove the blank page

    Not knowing what to share was the biggest barrier. Guided questions and AI follow-ups gave people a place to start.

  3. Short and regular wins

    People wanted short sessions of 10–15 minutes and gentle prompts, not long sittings.

  4. Family comes first

    In the card sort, family life and personal growth were the strongest themes, then work and career — that became the question structure.

04 My role

Lead designer. Every surface, end to end.

“I designed Valinor from the first survey to the admin panel — the conversation design, the storybook, the digital twin, the gifting flow and the visual identity.”
  • Research: the survey, the card sort and the persona
  • Competitive analysis of StoryWorth and Ancestry
  • Information architecture shaped by the card-sorting themes
  • Conversation design for the AI interviewer and the digital twin
  • Sketches, wireframes and concept testing
  • High-fidelity UI for the web app, gifting and subscriptions
  • The admin panel: users, plans, questions and content
  • The visual language, the mascot and the design system from 0 → 1
Stage
0 → 1, then redesign
Users
Storytellers 60+ · Families · Admins
AI
ChatGPT for questions, follow-ups and the twin
Team
Client, developers and the design team
Tools
Figma, FigJam, paper sketches
05 Platform modules

From a first memory to a family conversation

Everything I designed across the app and the admin panel.

  1. Onboarding

    “Who will be preserving their stories?” — yourself or someone else — then a short profile set-up and a mic test.

  2. AI interview

    Parent questions with AI follow-ups, progress like “05/15 answered”, regenerate a question or skip it.

  3. Voice or text answers

    Record an answer and Valinor converts it to text you can edit before saving — or simply type.

  4. Question library

    Fifteen core questions, themed sets like family, school, partner and travel, hidden questions and your own.

  5. Storybook

    Every answer as a story with photos, original recordings, word counts and edit history.

  6. Privacy & sharing

    Each story is public or private, can be hidden, and is shared by SMS, email or link.

  7. Digital twin

    A chatbot trained on your stories that answers your family in your words, with sample prompts to start.

  8. Family access

    Invite relatives with a relationship and an access level — viewer or admin — and manage who sees what.

  9. Gifting & plans

    Give Valinor as a gift with a scheduled date and a message; plans, a free trial and billing history.

  10. Admin panel

    Revenue and trial metrics, users and blocked users, plans, interview questions, CMS pages and settings.

06 Deep dive 1 · The core experience

Recording a life by having a conversation

The first and most important job was helping people record their experiences in a way that suited their age and their comfort with technology. Forms and blank text boxes were out: they recreate exactly the pressure that stopped people writing in the first place.

So recording became an interview. Valinor asks a parent question, then an AI follow-up based on the answer — the way a curious grandchild would. People can answer out loud; Valinor converts the recording to text they can check before saving. A mic test, a progress count and the option to regenerate or skip a question keep every session short and safe.

I sketched four layouts: a single chat, a sequence of cards, stacked cards and a split view. Testing pointed to a focused, one-question-at-a-time interview, with the full list of questions living in the storybook — so people always know where they are without being overwhelmed.

The problem

  • Writing long answers was tiring and, for some, physically painful.
  • A blank page left people unsure what to share or how to start.
  • Long sessions made people give up halfway through.

What I designed

  • A parent question and an AI follow-up, one at a time, with “05/15 answered” progress.
  • Voice answers converted to editable text, plus a mic test before the first recording.
  • Regenerate, skip and resume, so people record in short sessions at their own pace.

Why this, not thatI didn’t make the AI ask everything at once. A long list of questions felt like homework; one question and a thoughtful follow-up felt like someone listening.

Answer by voice — Valinor turns the recording into text you can edit before you submit.
Follow-ups — the AI builds the next question from what was just said.
07 Deep dive 2 · Where stories live

A storybook that grows with every answer

Answers on their own are just text. People wanted to see their life take shape — and to decide who gets to see which part of it.

Every answer becomes a story in the storybook: the question, the words, the photos that go with it and the original recordings, so the family can hear the real voice behind the text. Word counts and edit history show progress without turning it into a score.

Privacy sits right beside each story, not hidden in settings. A story can be public or private, hidden, or shared by SMS, email or a link — because some memories are for everyone and some are not.

The problem

  • Answers were a wall of text with no photos and no voice.
  • People couldn’t choose which stories each relative saw.
  • Sharing a single story meant sharing everything.

What I designed

  • Stories with photos, original recordings, word counts and edit history.
  • A public/private switch and “hide story” on every story.
  • One-tap sharing of a single story by SMS, email or link.

Why this, not thatI kept privacy on the story, not in a settings page. Decisions about what to share happen while reading a memory — that’s where the control belongs.

The storybook — each story with its photos, words, privacy and the original recording.
Share one story at a time — by SMS, email or a link.
08 Deep dive 3 · The AI idea

A grandparent the family can still talk to

Recording was only half of the promise. The stories had to reach the family — in a way that works whether a grandchild is four or forty.

The answer was a digital twin: a chatbot trained on the storyteller’s own stories, which answers questions the way they would. Family members get access through an invite with their relationship and an access level, then simply ask — starting from sample prompts if they don’t know where to begin.

My first idea reused the interview layout for chatting, for consistency. Testing showed it was too complex for a simple conversation, so I switched to a clean, focused chat. I also tried showing the storyteller’s photo beside the chat, but it took too much space from the conversation itself.

The problem

  • Printed books and family trees are one-way: you can read them, not talk to them.
  • Reusing the interview layout made a simple chat feel complicated.
  • A blank chat box left people unsure what to ask.

What I designed

  • A digital twin that answers in the storyteller’s own words and style.
  • Invites with a relationship and a viewer or admin access level.
  • Sample prompts and a clean chat focused on questions and answers.

Why this, not thatI didn’t keep one layout for both journeys. Consistency mattered less than fit: an interview needs structure, but talking to your grandparent should feel like just that.

Talk to the twin — sample prompts to begin, then a natural conversation.
Shared with you — every relative’s twin, their relationship and your access.
09 Gifting & plans

Valinor as a gift

10 Admin panel

The tools that run the platform

A product like this lives or dies on what happens behind the scenes. I designed the admin panel so a small team could run Valinor without a developer for every change.

Back office

Users, plans, questions and content — all editable by the team.

Pricing, interview questions and website pages change without a release, and every user’s plan, payments and answers are one click away.

  • Dashboard
  • User management
  • Plan management
  • CMS

Dashboard

Sales revenue, subscriptions, trial users and new sign-ups with trial and subscription dates.

Users & blocked users

Every user with plan, payment status and actions, plus a separate list to unblock accounts.

User profile

Profile answers, questions answered, chat messages used, plan sharing and billing history.

Plan management

Edit monthly and yearly prices, discounts, members and chat limits for each plan.

Interview questions

Add, edit and show or hide the questions every storyteller is asked.

CMS & settings

Edit website pages in a visual or HTML mode, show or hide homepage sections, and set reminder and data-retention limits.

11 Key challenges

What made this hard

Limited tech comfort

Many storytellers were new to apps like this. Voice answers, a mic test, large type and short sessions lowered the bar to a first story.

Modern enough for the young

The interface had to stay minimal and current so grandchildren would actually want to use it.

Stories that last

Stories, photos and recordings had to stay safe and shareable for years — with clear control over who sees what.

An AI that sounds like them

The twin had to answer in the storyteller’s own words and style, without feeling eerie.

Two buyers, one product

Often the person paying isn’t the person telling the stories. Gifting, scheduled dates and invites served both.

A first AI product

It was the company’s first AI project, so every conversation pattern was designed and tested from scratch.

12 Visual identity

Calm, warm and a little playful

A visual language that respects older users and still feels fresh to younger ones — anchored by a friendly robot guide.

Colour
A violet-to-purple palette on soft white, with gentle tints for question cards, chat and the purple footer.
Typography
A clean, humanist sans with generous sizes and spacing for readability.
Mascot
A friendly 3D robot guide across the landing page, onboarding, empty states and the 404 page.
Accessibility
Large tap targets, readable type, voice input and clear states for users of every age.
13 Impact

What the design changed

+30%

User engagement after the redesign of the core experience.

Source: product analytics, Biz4Group

WritingTalking (from Writing to Talking)

People record by speaking with an AI that asks and follows up, instead of facing a blank page.

Source: shipped product

TextStorybook (from Text to Storybook)

Answers become stories with photos, original recordings and per-story privacy.

Source: shipped product

One-wayTwo-way (from One-way to Two-way)

Families don’t just read the stories — they ask questions and get answers from the storyteller’s twin.

Source: shipped product

Hard askGift (from Hard ask to Gift)

Children can give Valinor to a parent, scheduled for a birthday, with a personal message.

Source: shipped product

DeveloperAdmin (from Developer to Admin)

The team changes prices, questions and website pages without a release.

Source: shipped product
14 Learnings

What Valinor taught me

  1. Ask the real users early

    The survey changed the product: voice answers came straight from older adults telling us writing was hard.

  2. Consistency isn’t always right

    The interview and the chat needed different layouts. Forcing one onto both made the simpler task harder.

  3. Design for the buyer too

    The storyteller and the person paying are often different people. Gifting made the product easy to say yes to.

  4. Design for the edges

    Choices made for older users — clarity, voice, short steps — made the product better for everyone.

Walkthrough

Want the full walkthrough?

Valinor is client work under NDA, so the product isn’t public. I’m happy to walk you through it on a call.

Stories outlive us.
Now they can answer back.

Valinor turns a life’s memories into a storybook and a conversation the family can keep having. Next, I’d explore the twin answering in the storyteller’s recorded voice, and family timelines that grow as more relatives add their stories.