Skip to content
SvorusSvorus
Case studyPortfolio case study

Glowskin: AI skin and hair coaching platform

Glowskin is an AI skin and hair coaching case study with a Flutter mobile app, FastAPI backend, Gemini image analysis, routine generation, ingredient scanning, subscriptions, tracking, and compliance pages.

Client label

Glowskin

Glowskin: AI skin and hair coaching platform

Challenge

A beauty and wellness AI product needs to make image-based insights feel useful without drifting into unsupported medical claims. Glowskin also had to manage sensitive biometric-style scan images, subscriptions, progress tracking, product ingredient intelligence, and a mobile UX built around camera capture and repeated check-ins.

Approach

The implementation pairs a Flutter app with a FastAPI backend. The scan flow validates and compresses images, optionally detects face landmark regions, stores scan images through S3-compatible storage, calls Gemini through Vertex AI, sanitizes model output, and records scan history. Separate services handle AI routines, contextual coaching, ingredient lookup and classification, Razorpay billing, Firebase notifications, Redis-backed limits, scheduler jobs, and compliance pages.

Technical profile

Architecture, capabilities, and implementation surface

Platforms

  • Flutter mobile app
  • FastAPI backend
  • Static compliance website

Technology

  • Flutter
  • Riverpod
  • GoRouter
  • Dio
  • Camera
  • Firebase Messaging
  • Razorpay
  • FastAPI
  • PostgreSQL
  • SQLAlchemy
  • Alembic
  • Redis
  • APScheduler
  • Google Vertex AI
  • Gemini
  • MediaPipe
  • Pillow
  • NumPy
  • S3-compatible storage
  • Sentry

Key features

  • AI skin and hair scan workflows from uploaded or camera-captured images
  • Skin score, skin age, hair score, detected concerns, top priority, and concern-zone outputs
  • Personalized skincare and haircare routine generation with AM, PM, weekly planner, and ingredient guidance
  • GlowCoach chat grounded in recent scans, active routines, and user profile context
  • Product label and barcode scanning for ingredient analysis and shelf saving
  • Habit logs, streaks, adherence scoring, progress charts, subscriptions, reminders, and account deletion flows

AI capabilities

  • Gemini Vision analysis for skin and hair images
  • Face-landmark-assisted skin concern zones using MediaPipe-derived regions
  • Gemini-generated personalized routines from profile and latest scan context
  • Gemini Vision OCR for cosmetic product label ingredient extraction
  • Reference-table ingredient safety lookup with AI classification and personalized explanations
  • Contextual GlowCoach responses using profile, routine, skin scan, and hair scan history

Architecture highlights

  • Flutter app uses feature modules, Riverpod providers, GoRouter redirects, camera/image capture, Firebase Messaging, Razorpay checkout, and shared design-system widgets
  • FastAPI backend exposes versioned API groups for auth, users, scans, routines, tracker, chat, products, ingredients, programs, and subscriptions
  • PostgreSQL stores users, skin scans, hair scans, routines, habit logs, chat messages, ingredient references, product scans, subscriptions, and program progress
  • Scan pipeline validates and compresses images, detects face landmarks for skin scans, uploads scan images to S3-compatible storage, runs Gemini analysis, and stores sanitized results
  • Compliance website covers privacy, terms, account deletion, biometric scan handling, sub-processors, retention rules, and medical-disclaimer boundaries

Engineering challenges

  • Handling sensitive face and scalp imagery with deletion, retention, and account-erasure flows
  • Keeping AI wellness outputs bounded by validation, clamping, fallback responses, and non-diagnostic positioning
  • Combining deterministic ingredient-reference data with AI classification and explanations without letting AI override safety source-of-truth decisions
  • Coordinating freemium limits across scan history, routine regeneration, chat history, product intelligence, and subscription state
  • Building mobile camera, image upload, payment, notification, and progress-tracking flows around a production API

Product screens

Product interface assets

Glowskin onboarding screen describing AI skin scan and score tracking
Onboarding flow for AI skin scan and score tracking
Glowskin sign-in screen with email, password and Google sign-in options
Authentication screen from the Flutter app

Results

What this entry is meant to prove

AI vision

skin, hair, and cosmetic label analysis with Gemini and MediaPipe-assisted concern zones

Full-stack

Flutter app, FastAPI backend, PostgreSQL data model, S3-compatible media, Firebase, Razorpay, and compliance website

Wellness-safe

validation, fallback responses, medical-disclaimer boundaries, retention notes, and account deletion support

Services involved

Capabilities behind this work

Agentic AI and Applied AI EngineeringProduction AI agents that plan, use tools, and act with evaluation, logging, and human oversight.Selected capabilitiesAgent design and orchestrationRetrieval and knowledge systemsEvaluation and guardrailsExplore serviceProduct Engineering and Custom SoftwareWeb, mobile, and platform engineering from discovery through production with one accountable team.Selected capabilitiesProduct strategy and discoveryWeb application engineeringMobile engineeringExplore serviceCloud, DevOps and Platform EngineeringCloud migration, CI/CD, observability, reliability, and platform foundations built for on-call reality.Selected capabilitiesCloud migration and modernizationCI/CD and DevOps automationSite reliability engineering and observabilityExplore serviceData Engineering and AnalyticsTrusted pipelines, data platforms, BI, and MLOps foundations for products, dashboards, and AI agents.Selected capabilitiesData pipeline and integrationData platform modernizationAnalytics and BIExplore serviceManaged Services and SupportApplication, cloud, and AgentOps support from the team that understands what was built and why.Selected capabilitiesApplication managed servicesCloud infrastructure managementAgentOps monitoringExplore service

Industry context

Market connected to this work

Retail and EcommerceCommerce engineering for conversion, inventory, personalization, and operations.

Related work

Other portfolio entries with overlapping architecture or service patterns

Related entries are selected from shared service pillars, industries, portfolio category, and technology overlap. Sample placeholders are kept out of recommendations when stronger entries are available.

Eleviy: AI fitness and nutrition product
Svorus productIn-house product
Svorus-owned product

Eleviy: AI fitness and nutrition product

Eleviy is a Svorus-owned AI fitness and nutrition product with a Flutter mobile app, FastAPI backend, multimodal meal analysis, personalized coaching, and workout generation.

FlutterRiverpodGoRouterDrift
Svorus-ownedin-house AI fitness and nutrition product
Multimodal AImeal photo analysis, coaching, and workout generation
View related entry
SupportOps Agent: AI support workflow lab
Svorus LabInternal R&D concept
Svorus Lab

SupportOps Agent: AI support workflow lab

SupportOps Agent is a Svorus Lab concept for AI-assisted support operations with ticket triage, retrieval, tool calls, human approval gates, and agent observability.

OpenAI Agents SDKNext.jsFastAPIPostgreSQL
Lab conceptnot represented as shipped client work
AgentOpstraces, approvals, evaluation, cost, latency, and tool-failure monitoring
View related entry
Enterprise RAG Copilot: document intelligence lab
Svorus LabInternal R&D concept
Svorus Lab

Enterprise RAG Copilot: document intelligence lab

Enterprise RAG Copilot is a Svorus Lab concept for private document intelligence with ingestion, hybrid retrieval, cited answers, governance, and evaluation loops.

LangChainLlamaIndexNext.jsFastAPI
Lab conceptoriginal Svorus R&D direction, not client work
Cited RAGanswers grounded in retrieved sources, metadata, and permission checks
View related entry

Need a product, agent, or platform with this level of engineering depth?

Bring the context, constraints, and desired outcome. We will help decide what should be validated and built first.

Book a callExplore services