Can I vibecode Lateral?

Build a deliberately narrow personal substitute for Lateral, not a full clone.
Use exactly this stack: Next.js 15 + TypeScript + SQLite + Playwright.
Primary job: Build a private research workspace that imports user-supplied URLs or files, extracts metadata, supports notes, and searches the local corpus.
Start from an empty folder and create the complete working project.

Functional Requirements:
- Document Import: Build an ingestion pipeline using Playwright to scrape text from URLs or local PDFs. 
- Metadata Extraction: Automatically extract title, author, publication date, and key terms from the ingested documents.
- Workspace UI: Implement a split-pane interface with a document reader on the left and a rich-text note-taking pad on the right.
- Local Search: Implement a fast, local full-text search across all imported documents and user notes.
- Highlights & Citations: Allow users to highlight text in the document reader and click to insert a linked citation directly into their notes.

Architecture & State:
- Make the default mode single-user and private.
- Store user data, extracted text, and notes locally in SQLite to ensure privacy and offline capability.
- Do not add analytics, telemetry, ads, or third-party accounts.
- Put every secret and external credential in .env and provide .env.example.

UI/UX & States:
- Implement the smallest polished interface that completes the core loop end to end.
- Include clear empty (no documents), loading (during Playwright scraping), validation, success, and failure states.
- Add import and export so the user is not trapped in the app (e.g., export notes to Markdown).
- Use accessible keyboard navigation, labels, focus states, and sensible contrast.

Security & Constraints:
- Validate untrusted input and never log secrets or private file contents.
- Deliberately exclude these paid-product advantages: publisher-specific import reliability for paywalled journals; citation graph scale; team libraries and institutional access.
- Do not fake integrations, network effects, proprietary data, model quality, compliance, or security claims.

Testing & DevOps:
- Write focused unit tests for the data model, text extraction parser, and the most important workflow.
- Add one end-to-end smoke test that proves the core loop works.
- Create a README with setup, permissions, architecture, data location, backup, and limitations.
- Add scripts for install, development, test, build, and a production-style local run.
- Run the tests and build before finishing, then fix errors rather than merely describing them.