This is a Next.js project bootstrapped with create-next-app.

First, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.

To learn more about Next.js, take a look at the following resources:

• Next.js Documentation - learn about Next.js features and API.
• Learn Next.js - an interactive Next.js tutorial.

You can check out the Next.js GitHub repository - your feedback and contributions are welcome!

The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.

Check out our Next.js deployment documentation for more details.

RetrospectIQ is a Next.js and TypeScript prototype that uploads building permit PDFs to AWS S3, stores permit metadata in MongoDB, extracts PDF text, runs OpenAI-assisted building profile extraction, and displays rule-based retrofit recommendations on a permit dashboard.

To run the app locally:

npm install
npm run dev

Open http://localhost:3000, then use the landing page CTAs to upload a permit or view existing permits.

Create a local .env.local file with the server-side credentials below. Do not commit this file.

MONGODB_URI=
AWS_REGION=
AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=
AWS_S3_BUCKET_NAME=
OPENAI_API_KEY=

MONGODB_URI should point to the MongoDB database used by the app. The AWS variables should allow PDF upload and download for the configured S3 bucket. OPENAI_API_KEY is used only by server-side analysis code.

The Phase 7 analysis route uses the OpenAI API to convert extracted permit text into a structured building profile. Configure OPENAI_API_KEY in .env.local before running AI analysis from a permit dashboard.

The app instructs the model to avoid hallucinating and to return null for unknown fields. The resulting profile is saved in MongoDB and then passed into the prototype TypeScript scoring logic.

Run the deterministic demo seed whenever you want to refresh the portfolio data:

npm run seed

The seed process is safe to re-run. It removes and recreates the same fixed demo records, so it does not duplicate data. Seeded records include Atlanta-area buildings, scored permits, building profiles, retrofit recommendations, and one scanned PDF example.

1. Visit / to see the RetrospectIQ landing page.
2. Open /permits to review seeded demo permits.
3. Open a permit dashboard to see building profile data, retrofit impact score, savings estimates, detected upgrades, and recommendations.
4. Visit /upload to upload a text-based PDF permit.
5. Open the uploaded permit dashboard and click Run AI Retrofit Analysis to exercise the S3 download, PDF extraction, OpenAI analysis, MongoDB persistence, scoring, and dashboard refresh workflow.

npm run dev
npm run lint
npm run build
npm run seed
npm test