Eat with your mood
An AI-powered meal planning experience that adapts to how you feel, what you have on hand, and what your goals are — so meal decisions become fast, personal, and healthier over time.
Product Overview
Problem
People struggle with daily meal decisions due to mood, time, diet constraints, and not knowing what to cook with available ingredients — leading to unhealthy choices and wasted groceries.
What it solves
The app detects your mood, remembers preferences, and recommends meals you can actually make — then explains why each option fits your mood and nutrition goals.
Mood-aware recommendations
Suggests meals based on user mood and preferences, with easy swaps for dietary needs.
Ingredient-first planning
Add available ingredients; the AI prioritizes recipes that use what you already have.
Nutrition tracking
Calories plus macro/micro estimates per meal, with daily summaries.
Explainability
Shows "why this meal" — mood fit, ingredients matched, and nutrition goal alignment.
Impact
Expected reach and outcomes for 2026.
~1,000+
Users / signups
~300+
Monthly active users
~25–35%
30-day retention
10–15 min
Time saved per plan
Traction Signals
- Users returning to re-plan meals weekly
- Positive feedback on "why this meal" explanations
- Increased usage when ingredient-based planning is enabled
Milestones
MVP shipped: chat-based meal planning + preferences
Mood detection + personalized recommendations + dashboard
Voice interaction prototype + roadmap to health-cycle features
Scale: partnerships, subscriptions, expanded tracking
Team
Who built it and how we contribute to the community.
Madan Venkatesh
Senior Software Engineer — AI Specialist
What they do
Owns end-to-end product (UX → APIs → LLM orchestration). Builds mood detection, meal logic, dashboards, and integrations.
Community impact
Drives weekly demos, ships new features, and supports other teams with reusable AI patterns (RAG/chat, evals, deployment).
Shree Vamshika Manandi
Senior Software Engineer — Full Stack
What they do
Implements UI flows, onboarding, responsive design, and performance optimizations.
Community impact
Maintains shared UI components, helps other B360U teams move faster with consistent design patterns.
Sairam Konda
Senior Software Engineer — Full Stack
What they do
Improves recommendation quality, evaluates mood signals, and iterates on explainability.
Community impact
Creates evaluation dashboards and documentation so other teams can reuse model testing practices.
Tech Stack
Frontend
Next.js (App Router) + Tailwind CSS
AI layer
LLM-powered chat + recommendation logic
Mood detection
Text sentiment + optional voice tone analysis
Data
User preferences, ingredients, meal logs
Deployment
Vercel / Docker / Cloud
Observability
Basic analytics + feedback loop for tuning