Ingrify

AI-powered ingredient scanning app that improved trust for Indian grocery shoppers

4.5 Star Ratings

Ingrify was created to address a growing frustration shared by everyday consumers that is ingredient labels are confusing, inconsistent, and often unreadable, making it hard to know what’s actually safe to eat.

I collaborated across teams to gather user feedback and created the app's user experience, interface with seamless access to brand values.

Role

Product Designer

Project Type

Health & Fitness, Tech

Timeline

Jan'25– May'25

Team

1 Designer , 1 PM , 4 Devs

Role & Impact/

Research

Performed competitor analysis, created user-personas , conducted 4 user interviews and 2 rounds of user testing, and synthesized insights into actionable design ideas.

Design

I joined as the sole designer after the dev-prototype was build and feasibility was proven, I rebuilt the experience from the ground up. I established the product’s visual identity and keeping it intact throughout the design process.

CHALLENGE

How do we help everyday Indian shoppers understand ingredients instantly?

Problem Discovery/

Backstory

The goal was to help users quickly understand what’s inside packaged food. To achieve this, the product team initially built an AI-powered prototype using OCR to extract and explain ingredient labels across any product.

Problem

Ingredient labels are widely confusing, but confusion alone doesn’t drive behavior. Existing solutions break at the moment users need them most and existing solutions in the market were of no help either:

• AI scans depend heavily on image quality and label consistency, leading to missed or inaccurate insights.

• Barcode-based apps often provide generic rating ignoring the individual needs and most of them fail for Indian products.

Ingredient labels are widely confusing, but confusion alone doesn’t drive behavior. Existing solutions break at the moment users need them most:

• AI-only ingredient scans depend heavily on image quality and label consistency, leading to missed or inaccurate insights.

• Barcode-based apps often fail for Indian products or return “product not found,” breaking trust.

• Generic health scores ignore individual dietary needs, making results feel irrelevant or unsafe to act on.

As a result, users either abandon the check entirely or fall back on branding and claims instead of facts.

Ingredient labels are widely confusing, but confusion alone doesn’t drive behavior. Existing solutions break at the moment users need them most:

• AI-only ingredient scans depend heavily on image quality and label consistency, leading to missed or inaccurate insights.

• Barcode-based apps often fail for Indian products or return “product not found,” breaking trust.

• Generic health scores ignore individual dietary needs, making results feel irrelevant or unsafe to act on.

As a result, users either abandon the check entirely or fall back on branding and claims instead of facts.

Same product different result

Design Solutions/

Building a MVP

INGRIFY PHASE 1 : Building a MVP

Through stakeholder discussions and competitive analysis, I proposed introducing barcode scanning as the primary entry point, with AI ingredient analysis as a fallback when products weren’t available in the database.

The MVP was designed to validate three things:

• User intent — Whether users prefer scanning barcodes over manual ingredient capture

• Trust & accuracy — Barcode scan for reliability and AI as fallback for coverage.

• Feasibility at scale — Ensuring insights were delivered quickly without over-relying on AI

Before I joined, the product existed as a technical prototype focused solely on AI-based ingredient analysis. It validated technical feasibility but did not yet meet user expectations or market norms for food-scanning apps.

To define a true MVP, I worked closely with stakeholders to align on what success should look like post-launch. Based on user behavior, competitor patterns, and trust signals, we identified barcode scanning as a critical entry point especially for new users while retaining AI ingredient analysis as a fallback for missing products.

Barcode Scan

AI Ingredients Scan

Beyond the MVP

INGRIFY PHASE 1 : Building a MVP

After launch, early usage showed users were actively scanning products. While the core experience worked, real-world usage revealed patterns that the MVP wasn’t designed to handle at scale.

As scans increased, new challenges surfaced. Repeated AI scans for the same products raised operational costs, while image quality and inconsistent labels affected accuracy and trust. 0

Onboarding & Personalization

Captures dietary preferences and allergens early so scores and warnings adapt to individual needs.

Add Products

Added to convert repeated AI scans into shared database improvements, reducing cost while expanding Indian product coverage.

Scan History

Introduced to let users revisit past scans without re-scanning, reducing friction and reinforcing confidence in results.

Buy Products and Report a Problem

Allows users to flag inaccuracies, creating a feedback loop that improves trust and data quality over time.

Buy Products and Report a Problem

Research/

Primary Research

I ran a quick survey with 30+ participants and 4 user interviews with everyday Indian consumers. Even with a small sample size, clear patterns emerged…

Secondary Research

I conducted Secondary research using existing studies, industry reports, and public discussions around food labels in India

I conducted desk research using existing studies, industry reports, and public discussions around food labels in India. Rather than only validating that ingredient labels are confusing, we focused on why and when users feel compelled to act. The goal was to understand the moments that justify pulling out a phone mid-shopping and scanning a product.

We identified that confusion alone doesn’t drive behavior perceived risk and decision anxiety do.

Key Insights

Relevance

People with allergies or dietary restrictions expect insights tailored to them, not generic ratings.

Relevance

People with allergies or dietary restrictions expect insights tailored to them, not generic ratings.

Relevance

People with allergies or dietary restrictions expect insights tailored to them, not generic ratings.

Simplicity

Most want quick Good vs Bad ingredient clarity first, with deeper breakdowns only when needed.

Simplicity

Most want quick Good vs Bad ingredient clarity first, with deeper breakdowns only when needed.

Simplicity

Most want quick Good vs Bad ingredient clarity first, with deeper breakdowns only when needed.

Personalization

People with dietary restrictions want products that match their health needs

Personalization

People with dietary restrictions want products that match their health needs

Personalization

People with dietary restrictions want products that match their health needs

80%

notice labels but rarely read ingredients

20%

engage with ingredient or nutrition details

60%

find labels hard to understand

80%

notice labels but rarely read ingredients

20%

engage with ingredient or nutrition details

60%

find labels hard to understand

80%

notice labels but rarely read ingredients

20%

engage with ingredient or nutrition details

60%

find labels hard to understand

Insights from NCBI

User Persona

It captures the strongest patterns from prospect users and guides initial design decisions while leaving room to evolve as more real user data comes in.

Competitor Analysis

I analyzed competitors like TruthIn, Yuka, TrashPanda to understand how users move from scanning to interpretation. Most relied heavily on database coverage and generic health scores, which struggle with Indian products and personalized needs.

User flows

By prioritizing clarity and speed, the flow keeps the experience effortless and reduces decision fatigue.

Testing & Iterations/

Internal Testing was done to quickly validate core flows, this helped identify technical edge cases, performance issues, and accuracy gaps. Based on user feedback and testing the product underwent few round of iterations. Key insights from user feedback included:

Design Decisions & Trade-offs/

Barcode vs AI scan

Barcode for speed and accuracy on known products; AI as fallback when data is missing.

Barcode vs AI scan

Barcode for speed and accuracy on known products; AI as fallback when data is missing.

Barcode vs AI scan

Barcode for speed and accuracy on known products; AI as fallback when data is missing.

Generic vs Personalized scoring

Generic scores reduce friction; personalization is layered in only when users opt in.

Generic vs Personalized scoring

Generic scores reduce friction; personalization is layered in only when users opt in.

Generic vs Personalized scoring

Generic scores reduce friction; personalization is layered in only when users opt in.

MVP speed vs Features

Non-essential features were cut to validate the core scan experience fast.

MVP speed vs Features

Non-essential features were cut to validate the core scan experience fast.

MVP speed vs Features

Non-essential features were cut to validate the core scan experience fast.

Automation vs System sustainability

Reducing repeated AI scans lowered costs and improved long-term scalability.

Automation vs System sustainability

Reducing repeated AI scans lowered costs and improved long-term scalability.

Automation vs System sustainability

Reducing repeated AI scans lowered costs and improved long-term scalability.

Success Metrics/

The success of this app and it’s features were measured by:

📈 Adoption & Engagement

Growth in active users and scan frequency, indicates that users found real value in scanning products.

📈 Adoption & Engagement

Growth in active users and scan frequency, indicates that users found real value in scanning products.

📈 Adoption & Engagement

Growth in active users and scan frequency, indicates that users found real value in scanning products.

⭐ Trust & Satisfaction

High app ratings and repeat usage, validates that ingredient insights were clear, and easy to act on.

⭐ Trust & Satisfaction

High app ratings and repeat usage, validates that ingredient insights were clear, and easy to act on.

⭐ Trust & Satisfaction

High app ratings and repeat usage, validates that ingredient insights were clear, and easy to act on.

🧠 Coverage & Cost Efficiency

Improved product database through user-added products, reducing repeated AI analysis costs.

🧠 Coverage & Cost Efficiency

Improved product database through user-added products, reducing repeated AI analysis costs.

🧠 Coverage & Cost Efficiency

Improved product database through user-added products, reducing repeated AI analysis costs.

Key Learnings/

INGRIFY PHASE 1 : Building a MVP

Collaboration & Communication

I learned the importance of close collaboration with stakeholders and developers in an early-stage product. I learned how to take a stand on design decisions by backing them with user research, competitive insights, and clear success metrics rather than opinions. This helped align teams, navigate trade-offs around cost and feasibility, and ship decisions that balanced user trust, technical constraints, and business goals.

Designing for imperfect data

Working with third-party databases meant scan failures, mismatches, and incomplete results were inevitable. Instead of hiding these limitations, we designed clear fallbacks ingredient scan, AI analysis, and user reporting to keep the experience intact even when the system wasn’t perfect.

What's Next?

INGRIFY PHASE 1 : Building a MVP

Point Based Reward System

A reward system where users earn rewards for adding verified products and referring others. This aims to encourage high-quality contributions while keeping database growth community-driven and sustainable.

Quiz

Add learning moments that help users understand ingredients over time and keeps engagement high without disrupting the core scan flow.