{"slug": "my-colleague-was-tired-of-saying-paneer-bhaji-again-to-his-maid-so-i-built-a-ai", "title": "My Colleague Was Tired of Saying “Paneer Bhaji Again” to His Maid. So I Built a Local AI Menu Planner.", "summary": "A developer built Aaj Kya Banega, a local-first meal planner that combines rule-based ingredient matching with Gemma 3 running via Ollama to suggest recipes from what's already in a user's fridge while avoiding recently cooked meals. The app returns structured JSON recipe data, including available and missing ingredients, prep time, and a short instruction message intended for a household cook, and is designed so fridge inventory and dietary habits stay on-device rather than going to a cloud API. The developer plans to add a WhatsApp or SMS handoff for sending the cooking instructions directly.", "body_md": "*This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)*\n\nA colleague from my office lives alone and has a maid who cooks at home.\n\nThe problem was not that food was unavailable. His fridge usually had eggs, paneer, spinach, chicken, onions, tomatoes, and the usual basics. The problem was deciding what to make.\n\nMost evenings ended the same way:\n\n“Paneer bana dete hain.”\n\n“Egg bhurji kar lete hain.”\n\n“Chicken curry?”\n\nAfter a few weeks, even good food starts feeling repetitive.\n\nSo I built **Aaj Kya Banega**, a local AI kitchen companion that recommends meals based on what is already in the fridge, what you've cooked recently, and how much time you have.\n\nThe app lets him:\n\nThe core question is simple:\n\nWhat can I make today without getting bored of eating the same thing again?\n\nA local-first meal planner for the daily question: **what should we cook today?**\n\nBuilt for a colleague who lives alone and was tired of deciding what to tell his maid to cook every day. With a full fridge but the same paneer bhaji appearing again and again, he needed more than another recipe website. He needed a simple, private way to decide tomorrow's meal.\n\nAdd what is in the fridge, explore recipes that fit, shuffle tomorrow's menu, and keep a lightweight record of what was cooked.\n\n```\nnpm install\nnpm run dev\n```\n\nOpen [http://localhost:3000](http://localhost:3000).\n\nAaj Kya Banega is built with:\n\nThe app has two layers of recommendation.\n\nFirst, it uses a regular ingredient-matching system to identify recipes that already fit what is in the fridge. This is quick, predictable, and useful even without generating anything.\n\nThen, Ollama runs Gemma 3 locally to make the recommendations more personal. The model receives a focused kitchen context:\n\nAvailable ingredients:\n\nEggs, paneer, spinach, onion, tomatoes, green chillies\n\nRecently cooked:\n\nEgg bhurji, paneer butter masala\n\nPreferences:\n\nQuick Indian home-style dinner for two people.\n\nAvoid repeating recent meals.\n\nSuggest exactly three meal ideas.\n\nClearly mention what is already available and what needs to be bought.\n\nKeep the cooking instructions simple.\n\nReturn structured JSON only.\n\nThe model returns structured recipe data that the app can display cleanly:\n\n`{`\n\n  \"title\": \"Palak Paneer with Roti\",\n\n  \"whyItFits\": \"Uses spinach and paneer already available at home.\",\n\n  \"availableIngredients\": [\"spinach\", \"paneer\", \"onion\", \"garlic\"],\n\n  \"missingIngredients\": [\"cream\"],\n\n  \"prepTime\": \"30 minutes\",\n\n  \"maidInstruction\": \"Make palak paneer with roti for two people. Keep it mildly spicy.\"\n\n}\n\nThis keeps the AI useful without letting it become a vague chat interface.\n\nFor this project, open innovation matters because a kitchen is personal.\n\nA fridge inventory may sound harmless, but it can reveal habits, food preferences, budgets, dietary restrictions, and daily routines. My colleague should not need to send all of that to a cloud API just to decide dinner.\n\nWith Ollama and Gemma 3 running locally:\n\nThe next feature is a WhatsApp or SMS handoff.\n\nOnce a recipe is selected, Aaj Kya Banega should create a short cooking message that can be sent directly to the maid:\n\nToday: Palak Paneer with Roti\n\nFor: 2 people\n\nUse: spinach, paneer, onion, garlic\n\nBuy: cream\n\nPlease make it mildly spicy.\n\nThe current version already supports generating this instruction locally. The next step is connecting it to a messaging provider.\n\nI also plan to add:\n\nAaj Kya Banega uses Gemma 3 running locally through Ollama to recommend practical meals from ingredients already available at home. The model considers fridge inventory, recently cooked meals, cooking time, and dietary preferences while keeping the recommendation flow private and local.", "url": "https://wpnews.pro/news/my-colleague-was-tired-of-saying-paneer-bhaji-again-to-his-maid-so-i-built-a-ai", "canonical_source": "https://dev.to/kaustubhjogle/my-colleague-was-tired-of-saying-paneer-bhaji-again-to-his-maid-so-i-built-a-local-ai-menu-4n1m", "published_at": "2026-10-04 19:36:27+00:00", "updated_at": "2026-10-04 19:42:31.796892+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "ai-products", "developer-tools"], "entities": ["Aaj Kya Banega", "Ollama", "Gemma 3", "WhatsApp"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/my-colleague-was-tired-of-saying-paneer-bhaji-again-to-his-maid-so-i-built-a-ai", "markdown": "https://wpnews.pro/news/my-colleague-was-tired-of-saying-paneer-bhaji-again-to-his-maid-so-i-built-a-ai.md", "text": "https://wpnews.pro/news/my-colleague-was-tired-of-saying-paneer-bhaji-again-to-his-maid-so-i-built-a-ai.txt", "jsonld": "https://wpnews.pro/news/my-colleague-was-tired-of-saying-paneer-bhaji-again-to-his-maid-so-i-built-a-ai.jsonld"}}