PassionQA: Turning My Passion for Software Quality into AI-Powered Test Intelligence

This is a submission for Weekend Challenge: Passion Edition

What I Built

As a QA engineer, I spend a lot of time reading requirements,

questioning unclear business rules, and thinking about what could break before a feature reaches users. That part of quality engineering is something I genuinely enjoy, and it inspired me to build PassionQA.

PassionQA is an AI-powered quality intelligence platform that turns product requirements into practical QA insights and executable test cases.

The workflow is simple:

1. Upload or paste a BRD (Excel or text)


2. Run AI-assisted quality analysis


3. Review the complete QA output in one dashboard:
   
   
   
   
   • Requirement health and release readiness
   
   
   • Missing rules and ambiguous requirements
   
   
   • Positive, negative, boundary, security, and accessibility test cases
   
   
   • Bug-risk insights and heatmap
   
   
   • Requirements Traceability Matrix (RTM)
   
   
   • Excel and PDF exports
   
   
   
   

My goal was to reduce the repetitive part of requirement analysis so testers can spend more time thinking critically about product risk and quality.

Demo

Try it quickly

Live app: https://passion-qa.vercel.app

• Click Explore Demo Preset to analyze the built-in insurance example. The application uses Gemini when available and automatically falls back to the local analysis engine if Gemini is unavailable.


• Or click Launch Platform (Free), upload your own BRD, and select Run Quality Analysis.

For my demo, I used an insurance Policy BRD. PassionQA analyzed the requirements, highlighted quality gaps, and generated executable positive, negative, boundary, security, and accessibility test scenarios across the policy workflow.

Video Demo

The demo shows the complete flow from Policy BRD upload to AI analysis, test-case generation, risk insights, RTM, and report export.

Demo video: https://drive.google.com/file/d/1sAoOauTGCk66xAzY46zF8_lWBQbVM8Gr/view?usp=sharing

Code

GitHub repository: https://github.com/DhanashriQAEngineer/PassionQA/

Some of the key parts of the project are:

• src/lib/gemini.ts --- Gemini analysis and local fallback engine


• src/app/api/analyze-requirement/route.ts --- server-side analysis
  API


• src/app/dashboard/page.tsx --- QA intelligence dashboard


• src/lib/excelExport.ts --- multi-sheet Excel export


• scripts/record-demo.mjs --- Playwright demo recorder

How I Built It

Why I built PassionQA

I didn't want to create another chatbot that simply summarizes a

document.

In QA, a summary is not enough.

We need to know what is missing, which requirements are unclear, what business rules could fail, and whether our test coverage is strong enough.

That is why I designed PassionQA more like a QA workspace or tester's cockpit. The dashboard focuses on test coverage, requirement health, risk, traceability, and executable test scenarios.

AI-powered requirement analysis with Google Gemini

Google Gemini is used as the AI analysis engine.

The BRD content is sent through a server-side API route with a QA-focused prompt. Gemini analyzes the requirements and returns structured information including product domain and modules, requirement quality metrics, missing or unclear business rules, executable test cases, risk areas, RTM data, and QA recommendations.

One important decision was to keep the Gemini API key on the server instead of exposing it in the browser.

The application also tracks whether the result was generated using Gemini or the local analysis engine, so the UI clearly shows the actual analysis source.

Reliable demo and fallback mode

PassionQA supports two analysis modes:

• Gemini mode for live AI-assisted requirement analysis


• Local mode as a fallback when Gemini is unavailable or times out

The Explore Demo Preset follows the same analysis flow. If Gemini is configured and available, Gemini performs the analysis. If the request fails or Gemini is unavailable, PassionQA automatically uses the local analysis engine.

The local mode still generates a complete QA dashboard, which keeps the application usable and makes the demo reliable.

Tech stack

I built PassionQA using Next.js App Router, React, TypeScript,

Tailwind CSS, Google Gemini, Recharts, Framer Motion, xlsx-js-style, jsPDF, and Playwright.

Decisions that mattered to me

The most important part of PassionQA is the generated test suite.

Dashboard metrics and test counts are based on the generated test cases rather than fixed demo numbers.

I also focused on keeping the AI experience transparent. If Gemini generates the result, the UI says so. If the application uses local fallback, that is clearly shown to the user.

Finally, I created a Playwright-based demo flow using a real insurance Policy BRD. This helped me validate the same experience a QA engineer would follow: upload requirements, analyze quality, review risks, inspect test cases, check traceability, and export the results.

Prize Categories

I am submitting PassionQA for Best Use of Google AI.

Gemini is not used as a simple chat feature. It is the core requirement-analysis engine that transforms BRD content into structured QA artifacts: requirement insights, executable test cases, risk areas, RTM mappings, and recommendations.

For me, this project combines two things I am genuinely passionate about: software quality and AI.

PassionQA started from a simple thought I often have while testing a product:

"What are we missing before this reaches production?"

This project is my attempt to help QA teams answer that question earlier and faster.