Skip to content

AI / Productivity

DayZy AI: Making day-out planning simple, smart, and social

An AI-powered day-out planning concept that acts as a co-planner: from mood and context to a suitable, practical plan instead of endless searching across apps.

Role
UI/UX Designer 
Team
Team of five
Duration
6 months
Status
Completed 
Tools
Figma and FigJam

Outcome: A concept/course project that shifts the experience from  Search → Compare → Decide to Mood → Context → Recommendation → Plan → Experience.  This was not a production product; no business metrics are claimed.

AIProductivityMobileSocial
VIEW INTERACTIVE  PROTOTYPEDayZy AI cover artwork — an AI day-out planning app concept

Problem context

What was actually going wrong

What problem existed

Planning a day out involves deciding what to do, choosing where to go, considering mood and group preferences, checking distance and travel, comparing options, gathering useful information and coordinating with others.

Who experienced it

College students, working professionals and non-working individuals in Bangalore and other cities/towns across Karnataka; the product was envisioned for Indian users more broadly.

Why it mattered

Information exists across multiple platforms, and the user becomes the connector between all those systems. The challenge isn't finding more places — it's deciding what to do next.

What was known

Five-member team research with 8–10 participants using qualitative and quantitative methods, covering mood, location, distance, travel, time, group and suitability, plus competitive analysis.

What still needs validation

Task completion, time to decision, recommendation relevance, planning effort, group decision time, confidence, recommendation acceptance and information sufficiency — all metrics to be validated.

Research lens

How people planned day-outs before DayZy.

  • Before DayZy, planning was distributed across different digital platforms.
  • A typical journey: Discover a place → Check reviews → Check location → Discuss with friends → Compare → Check travel → Decide.
  • The information existed. The user had to connect it.

Research lens

The people, places, and context shaping day-out decisions.

  • Primary research environment: Bangalore, Karnataka, India.
  • Research participants included college students, working professionals and non-working individuals, from Bangalore and other cities/towns across Karnataka.
  • The product was envisioned for Indian users more broadly.
  • Device: mobile. Context: Indian lifestyle, social discovery, day-out planning and AI recommendation.

Research lens

Understanding the friction between discovering options and making a plan.

  • Core journey: Set Mood / Intent → Get Relevant Experiences → Explore & Compare → Check Context → Plan With Group → Finalize → Book / Go.
  • Top tasks: decide what to do, find an experience that fits the context, turn the choice into a plan.
  • Major friction: choice overload, fragmented information, group decision-making, distance and travel, insufficient decision context.
  • Core friction: the user gets stuck between discovering possibilities and committing to one practical plan.
  • Simplification: Feel → Understand → Choose → Plan → Go, instead of Search → Browse → Compare → Switch apps → Discuss → Re-search → Decide.

Research lens

How emotions, trust, and AI shape the planning experience.

  • Starting emotion: uncertain — with confusion, frustration, decision fatigue and timing anxiety along the way.
  • Trust issue: trusting AI-generated recommendations.
  • Desired emotional progression: Uncertain → Curious → Reassured → Confident → Excited.
  • Visual direction: blue + green, aiming for trust, freshness, positivity and exploration.
  • Interaction: guided decision-making instead of endless searching.

Research lens

How users search, compare, discuss, and eventually decide.

  • Existing behaviour: Search → Compare → Check reviews → Check distance → Ask friends → Find another option → Compare again → Decide.
  • Workaround: users combine discovery platforms, maps, reviews, messaging apps and booking/information platforms.
  • Habit loop: Trigger → Search → Compare → Discuss → Uncertainty → Search again → Decision.
  • Desired behaviour: tell DayZy what kind of experience you're looking for → review relevant options → choose → plan.
  • Feedback loop: Mood → Recommendation → User choice → Plan → Experience → Feedback. The concept does not assume AI perfectly understands emotions.

Research lens

What the research tells us.

  • Research sample: 8–10 participants (qualitative and quantitative methods).
  • Usability testing: not yet established / not conducted.
  • Task completion: not quantitatively measured.
  • Time saved: not quantitatively measured.
  • Errors: not measured. Confidence: not formally measured. Business impact: not measured.
  • Metrics to be validated: task completion rate, time to decision, recommendation relevance, planning effort, group decision time, confidence, recommendation acceptance, information sufficiency.

Design engineering

The process, as it actually ran

Steps marked as pending were not part of this project. They are shown so the gaps stay visible.

  • Research — completed

    8–10 participants, qualitative and quantitative methods, studying outing-planning behaviour.

  • Analysis — completed

    Analysed mood, location, distance, travel, time, group and suitability as decision inputs.

  • Competitive analysis — completed

    Reviewed existing discovery, review, maps and booking platforms.

  • Mood-first approach — completed

    Explored mood and context as the starting point instead of search.

  • UX & IA — completed

    Structured the user experience and information architecture.

  • AI as co-planner — completed

    Designed AI interaction as a co-planner the user can guide and correct.

  • Mobile UI — completed

    Created the mobile interface.

  • Interactive prototype — completed

    Built an interactive prototype of the experience.

  • Usability testing — pending

    Not yet established / not conducted.

Information architectureInformation architecture — from splash and sign-in through mood selection into home, categories, AI bot, calendar, place details, payment and connect.
User flowEnd-to-end user flow covering onboarding, AI-assisted planning, groups, search, calendar, payments, reviews and booking.
Affinity mapResearch synthesis — grouped observations on mood, companionship, time, distance and activity choice.
Survey response boardUser responses arranged by survey question, colour-coded and grouped into patterns.

STAR story

Situation, Task, Action, Result

Situation

Planning a day out often requires users to search, compare, check reviews, evaluate distance, discuss options and decide — across multiple platforms.

Task

Explore how to reduce decision-making friction and help users move from 'I want to go out' to a suitable and practical plan.

Action

  • As part of a five-member team, researched 8–10 participants using qualitative and quantitative methods.
  • Studied outing-planning behaviour and analysed mood, location, distance, travel, time, group and suitability.
  • Conducted competitive analysis and explored a mood-first approach.
  • Structured the UX and IA, designed AI as a co-planner, created the mobile UI and an interactive prototype.
  • Independently developed the DayZy concept from the identified problem space.

Result

DayZy shifts the experience from Search → Compare → Decide to Mood → Context → Recommendation → Plan → Experience.  This was a concept/course project, so no production metrics or business impact are claimed. The strongest result is the design learning: the opportunity wasn't simply to help users find more places, but to help them make a better decision about what to do next.

Research lens

Testing

What was tested, with whom, and what was  and wasn't measured.

  • Research with 8–10 participants using qualitative and quantitative methods, in Bangalore and across Karnataka.
  • Competitive analysis of existing discovery, review, maps and booking platforms.
  • Usability testing was not conducted, so task completion, time to decision, recommendation relevance and confidence remain unmeasured.

Research lens

Iteration

What changed after feedback, and the reasoning behind each change.

  • Moved the entry point from search to mood after research showed the blocker was deciding, not finding.
  • Reframed AI as a co-planner the user can guide and correct, rather than an assistant that claims to read emotions.
  • Brought distance, travel and group context into the recommendation itself so users stop switching between apps.

Research lens

Impact

The honest outcome  measured where it exists, marked as unvalidated where it doesn't.

A concept/course project  no production or business impact is claimed. Metrics to be validated: task completion rate, time to decision, recommendation relevance, planning effort, group decision time, confidence, recommendation acceptance and information sufficiency. This information was not supplied for this project and has not been invented. — this information was not supplied for this project and has not been invented.

Before & after

What changed, and why

Before

Search → Browse → Compare → Switch apps → Discuss → Re-search → Decide — the user connects fragmented information across platforms.

After

Feel → Understand → Choose → Plan → Go — guided decision-making from mood and context to one practical plan.

What changed
Planning shifted from searching across platforms to a guided path from mood to plan.
Why it changed
The user gets stuck between discovering possibilities and committing to one practical plan; the challenge is deciding, not finding.
Supporting evidence
Impact to be validated — concept/course project, not measured in production.

Final screens

The interface

Key screens from the final design.

HomeHome — location, search, mood and category chips, with recommendations, offers and events in one place.
Mood-led AI chatAI chat — the assistant asks for mood first, then narrows down to a category before suggesting plans.
ChatChat — one-to-one and group conversations, where a plan is agreed with the people going along.
Mood selectionMood selection — the starting point of the flow, for users who begin from how they feel.
CalendarCalendar — a confirmed plan placed on a date, with time, place and the members going along.
DayZy MoneyDayZy Money — in-app balance and transaction history used to settle plan payments.

Field Research

Taking research beyond the screen

Our five-member team conducted field research in Bengaluru with a student and an IT professional.

My first field experience taught me how to listen, observe reactions, and understand the context behind people's answers.

From research to design, the conversations helped us challenge our assumptions and shape our DayZy solution.

COLLEGE STUDENT PARTICIPANT
IT PROFESSIONAL PARTICIPANT

Learnings

What this project taught me

  • The opportunity wasn't simply to help users find more places, but to help them make a better decision about what to do next.
  • AI is only useful here if the user can guide and correct it quickly; the interaction matters more than the model.
  • Reducing the number of decisions is itself the feature.

Next project

Togile CRM

Start a ConversationView Next Project