Urgent.News

What's breaking now, across thousands of outlets.

AI

DigiPico: I Built a Gamified AI Companion with Mastra & Gemma 4 to Help My Friend Fall in Love with Tech

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built I built DigiPico , a gamified, mobile-first AI learning companion designed specifically for a close friend of mine who doesn't particularly like tech. As a developer, I’ve always wanted to share my passion for software with her, but she has always found the tech world deeply intimidating, dry, and…

This week, I built a gamified AI learning companion named DigiPico for a friend who isn't fond of technology. As someone who loves software, I wanted to share my passion without scaring her off. The traditional tech learning platforms were too textbook-like and coding environments were too cold.

So, I created DigiPico, a cute blue penguin tutor, to make learning more interactive and fun. Pico breaks down complex concepts into bite-sized, playful challenges. The app adapts to her interests, generates quizzes, and creates safe JavaScript sandboxes for hands-on coding. Every correct solution earns her experience points and unlocks achievements.

When I finally handed the app to her, her reaction was amazing. She gravitated towards the cute penguin, spent an hour on the coding challenges, and said, "This is the first time programming actually felt like a fun puzzle game." That made the entire weekend worthwhile.

DigiPico is a Next.js full-stack application designed for mobile screens first. It uses Capacitor for seamless iOS and Android deployment. The AI agent is powered by Gemma 4, an open-weights model, with personalized explanations and hands-on challenges. It connects to MongoDB Atlas for user data, ElevenLabs for voice interactions, and SerpApi for sharing current tech news and hackathons. The whole app is deployed on Render via a single Web Service.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

SafePlate

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built My friend Aarav is allergic to peanuts, tree nuts and dairy.

  • SafePlate app helps allergy sufferers like Aarav
  • Uses open-weight LLM in browser via WebGPU
  • Provides SAFE, CAUTION, AVOID verdicts offline

I Built a CET Counsellor AI Agent for Maharashtra Engineering Aspirants — Sanity Challenge

What I Built CET Counsellor is an AI agent that helps Maharashtra engineering students navigate the confusing world of MHT-CET and JEE admissions — CAP rounds, category-wise cutoffs, required…

  • Developed AI assistant "CET Counsellor" for Maharashtra engineering aspirants
  • Addresses confusion around CAP admission rounds, categories, cutoffs, documents
  • Structured knowledge base in Sanity with React frontend and TanStack CMS

Ask-Docs Search: Choose Semantic Embeddings Over Keyword Search for SaaS Support

For a beginner ask-your-docs feature that triages incoming SaaS support tickets, choose embeddings-based retrieval over document chunks, then add reranking only if evaluation shows that the first-pass…

  • Semantic embeddings capture natural language nuances better than keyword search
  • Dual-layer approach recommended: semantic retrieval first, reranking second
  • Keyword search complements semantic retrieval for exact token detection

More from Sunday 4 October →