Designathon

2nd Position Award

Team of 7 · 22 hours

Travel planning with Agentic AI

WHAT I WORKED ON Interaction Design · Worked on Samsung Family Hub fridge touchpoint
Book the flight
Sort the ride to the airport with Ajay
Dig up Meera’s recommendations
Plan the day & check with the group
Pack for the trip
Empty the fridge
Order travel essentials

Samsung challenged us to design an agentic mobile assistant for a real-world travel scenario: helping a user named Sonia coordinate and book a weekend reunion with friends in Lucknow.

DELIVERABLES

· High-fidelity screens for all touchpoints

· How the agent shows its reasoning, asks for consent, & gives the user more ways to control it

· One bonus: a live camera feature of our choice

Sonia says ‘look for flights for this’ over a friend’s message. Aris reads the screen to work out what ‘this’ means

“Let’s look for flights for this”
WhatsApp Chat Prompt
SCAN SCREEN
Selected Reunion Message
SPECIFIC SCAN
Floating Aris Prompt
Flight Options Selection
Searching Flights Modal

Chain of thought made visible

Aris echoes her inputs back before acting, so she can correct a wrong assumption early

Payment Selection Modal

Consent gates the spend

Aris asks for the payment method, then needs an explicit confirm before it pays

Confirm Payment Modal

Aris keeps Sonia in the chat

A floating window handles the questions (answered by tap, voice or keyboard), search & booking

Sonia asks for a cab to the airport with a stop for Ajay. Aris books it & drafts a message to him for her approval

Home screen with Aris Cab Booking Widget
“Book me a cab to the airport, pick Ajay on the way”
Checking flight details & Uber booking

The floating window stays with her on the home screen

Aris works across apps so Sonia never has to jump back and forth

Cab scheduled confirmation
Message confirmation prompt for Ajay

Sonia stays in control

Aris drafts the message, but only sends it after she confirms

Sonia half-remembers a tip from Meera. Aris searches their past chats and pulls up the exact recommendations

“WHAT WAS THAT PLACE MEERA
TOLD ME ABOUT IN LUCKNOW?”
Past chat recommendation query Pulled up recommendation cards Search recommendation results overview

Edge case: human intervention

Human intervention captcha pause flow

When Aris hits something only a human can do, like a captcha, it pauses and hands control to Sonia, then resumes when she hands it back

Sonia asks for a day plan around Meera’s picks. Aris drafts it, shows her the exact message, and posts to the group only after she approves

“PLAN A DAY AROUND THESE PLACES AND
CHECK WITH THE GROUP IF THEY’RE UP FOR IT.”
Day plan chat interface
Drafted day plan itinerary
“this looks good! share it with my friends”
Group message confirmation

While Sonia packs, Aris reminds her about Matthew’s hoodie, a promise from an old chat. A long press shows where it came from

Always showing its work

Aris links every suggestion straight back to the original chat, so recommendations feel useful instead of invasive

Hoodie reminder card Original chat verification prompt
Packing reminder interface
“add it to my trip checklist”

Sonia asks Aris to help empty the fridge. Aris reads what’s about to expire, suggests recipes, and orders what’s missing

“I need to empty the fridge before I leave. Can you help?”
Samsung Family Hub fridge screen
recipe suggestion
Recipe suggestions view
“chicken curry looks good”

Always showing its work

Payment stays off the shared fridge screen, Aris pushes the request to Sonia’s phone for a quick confirmation & payment, then takes back control

order & approval for groceries
Confirm Blinkit payment approval card Ordered arrival status card

Sonia dictates her packing list. When Blinkit runs out of three items, Aris finds them on Zepto and shows both carts before she pays once

“add toothpaste and usual stuff to my list”
Voice list transcription

Aris explains store changes upfront

So she’s not caught of guard by two separate deliveries

Split store carts overview Consolidated payment authorization

Even with two different stores, she only has to confirm once

Sonia points her camera at the Bara Imambara. Aris highlights the exact structure on screen and explains what she’s looking at.

“what am i looking at? what’s so interesting about it?”
agent active on real time camera
Live viewfinder highlight
live feed feature: giving historic information
Historical context card on camera feed