惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
V
Visual Studio Blog
IT之家
IT之家
博客园 - 聂微东
The Cloudflare Blog
月光博客
月光博客
阮一峰的网络日志
阮一峰的网络日志
S
SegmentFault 最新的问题
Apple Machine Learning Research
Apple Machine Learning Research
酷 壳 – CoolShell
酷 壳 – CoolShell
爱范儿
爱范儿
H
Help Net Security
博客园 - 叶小钗
V
V2EX
WordPress大学
WordPress大学
J
Java Code Geeks
Hugging Face - Blog
Hugging Face - Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园_首页
C
Check Point Blog
B
Blog
D
DataBreaches.Net
美团技术团队
罗磊的独立博客

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Building VoteWise India: An AI-Powered Election Process E...
Advik Sharma · 2026-05-01 · via DEV Community

Building VoteWise India for PromptWars / Build with AI 2026

For PromptWars / Build with AI 2026, I built VoteWise India, a non-partisan election process education app for students and first-time voters. The goal was to make election learning feel interactive instead of turning it into a long page of civic studies notes.

The Problem

Many young learners understand elections mainly as the moment of voting. But an election is a full process: eligibility, registration, electoral rolls, candidate nomination, campaigning, polling day, EVM/VVPAT, counting, and results. If students only learn the final step, the rest can feel confusing or intimidating.

VoteWise India tries to make that process easier to understand through guided interaction.

I later reorganized the prototype from one long page into lightweight app-style views: Home, Learn, Simulator, AI Guide, Glossary, Quiz, Teacher Mode, and Settings. It still uses one HTML entry and no framework, but hash routes make it feel easier to navigate.

For judging, I added a 90-second tour on the Home view, a safe Google Services Status card, and a PromptWars evaluation card that maps the project directly to code quality, security, efficiency, testing, accessibility, and Google services.

The Idea

The app teaches by doing:

  • A journey map explains each election stage.
  • A before/during/after timeline gives learners a quick mental model.
  • A personalized pathway adapts learning for different users.
  • Scenario cards help learners pick a route based on their situation.
  • A searchable glossary and term tooltips explain hard words like Electoral Roll, VVPAT, NOTA, EVM, Constituency, and Model Code of Conduct.
  • FAQ items answer common first-time voter questions.
  • A misinformation check mini-game helps users practice spotting false claims.
  • A mock EVM/VVPAT simulator lets users experience a fictional vote flow.
  • A Gemini AI Election Guide answers process questions.
  • Myth vs fact cards correct common misunderstandings.
  • A VoteReady certificate quiz gives a score, weak topics, explanations, and next steps.
  • Teacher Mode gives a 5-minute activity, discussion questions, key terms, quick quiz idea, and answer key.
  • Accessibility settings include bigger text, high contrast, simple English, reduce motion, reading focus, theme shortcut, and reset controls.
  • Optional Firestore support can store anonymous quiz outcomes when deployed with Google Cloud.

The design goal was a polished civic-tech feel: clean, modern, serious, and approachable.

AI and Prompt Strategy

The AI guide uses Gemini only for election process education. The browser never sees the API key. Questions go to a Node server route, where they are validated before Gemini is called.

The Gemini instruction is intentionally narrow:

  • Explain the Indian election process.
  • Stay factual and beginner-friendly.
  • Do not recommend, rank, support, or oppose political parties or candidates.
  • Do not use real party or candidate names.
  • Refuse political persuasion requests and redirect to process education.

This makes the AI feature part of the learning system instead of a chatbot pasted onto a page.

Safety Guardrails

VoteWise India is completely non-partisan. It does not use real parties or real candidates in simulations. The mock voting simulator uses only Candidate A, Candidate B, Candidate C, and NOTA.

The AI guide blocks political recommendation questions before sending them to Gemini. For example, if someone asks who to vote for, the app refuses politely and offers to explain how voting works or how to evaluate information safely.

The app also includes a clear disclaimer: it is educational, non-partisan, and not an official Election Commission website.

Accessibility

Accessibility was treated as part of the actual product, not a footer claim. The app includes:

  • Keyboard-friendly controls.
  • Visible focus states.
  • Semantic headings.
  • Skip link.
  • Screen-reader-friendly status messages.
  • Bigger text mode.
  • High contrast mode.
  • Simple English mode.
  • Reduce motion mode.
  • Dark and light themes.

These features help make civic learning more usable for more people.

Testing

I added focused tests for the areas most likely to matter in a hackathon demo:

  • Quiz scoring.
  • VoteReady label ranges.
  • Weak topic detection.
  • Glossary search.
  • Misinformation answer checking.
  • VoteReady certificate defaults.
  • Hash route resolution for app-style views.
  • Political recommendation blocking.
  • VVPAT slip rendering after a simulated vote.

The tests use Node's built-in test runner, which keeps the project lightweight and easy to run.

Google Services

The project uses Gemini for the AI Election Guide. It is designed so the API key stays on the server through environment variables. The project can be deployed to Google Cloud Run or Firebase App Hosting, and the README explains how to configure Gemini securely.

I also added deployment-ready Google service support without pretending it is already live:

  • Firebase Hosting can serve the static frontend.
  • Firebase Hosting can rewrite /api/** requests to Cloud Run.
  • Cloud Run can run the Node backend.
  • Secret Manager can provide GEMINI_API_KEY in production.
  • Firestore can store anonymous quiz-result metadata if enabled.

What I Learned

The biggest lesson was that civic education apps need both clarity and restraint. It is easy to add more facts, more cards, and more UI. It is harder to make the experience calm enough that a first-time voter can understand what to do next.

I also learned that AI safety is not only about one prompt. The app needs layered protection: UI messaging, local validation, server-side blocking, model instructions, and clear disclaimers.

Future Improvements

Future versions could add:

  • Multi-language support.
  • More classroom activities.
  • Teacher dashboard mode.
  • Offline-first content.
  • A Firebase database for anonymous quiz analytics.
  • Voice narration for accessibility.
  • More detailed process modules with citations to official election education material.

VoteWise India is a small build, but the mission is important: help people understand the election process without pushing them toward any political choice.

Live app: https://votewise-india-api-366445017721.us-central1.run.app

GitHub: https://github.com/AdvikSharma917/votewise-india