Can AI replace Folk?

Build a personal replacement for Folk in an empty repository.
Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and Docker Compose; do not offer alternative stacks.
The core loop is: manage contacts and companies in relationship lists, enrich context manually, run lightweight outreach, move opportunities through a pipeline, log interactions, and surface the next action.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Create contacts, companies, opportunities, notes, tasks, and configurable pipeline stages.
Add fast global search, duplicate detection, merge, CSV import, and CSV export.
Provide a chronological interaction timeline with manual email and meeting logging.
Implement saved views, filters, owner assignment, and a next-action dashboard.
Add role-based access, an immutable activity log, backups, and a recovery command.
Seed a realistic demo workspace and document field mapping for imports.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Deliberately leave out automatic mailbox ingestion.
Deliberately leave out commercial enrichment databases.
Deliberately leave out enterprise forecasting, integrations, and compliance.
Finish by running the tests and listing the exact commands used.