Use Claude to Design and Write a Prisma Schema
Writing a Prisma schema from scratch means remembering relation syntax, deciding where to put @relation fields, and setting up indexes correctly. Let Claude draft the schema while you focus on your domain model.
Design a Prisma schema for a multi-tenant SaaS app with:
- Organisations (name, slug, plan enum: free/pro/enterprise)
- Users with organisation membership and a role enum
- Projects belonging to organisations
- Audit logs tracking who changed what and when
Claude will generate a complete schema.prisma with proper @relation annotations, @@index declarations, enum definitions, and createdAt/updatedAt timestamps. It adds @@unique constraints where they make sense (like slug on organisations) and suggests a Role enum for membership types.
model Organisation {
id String @id @default(cuid())
name String
slug String @unique
plan Plan @default(FREE)
members Member[]
projects Project[]
createdAt DateTime @default(now())
}
After reviewing the schema, follow up with "generate the initial migration" or "write Prisma seed data for local development" to keep moving.
Claude also handles trickier patterns like self-referential relations (parent/child categories) and polymorphic-style setups using separate join tables.
Describe your domain, and Claude will give you a Prisma schema that's production-ready on the first draft.
Log in to leave a comment.
Set up Claude Code as an automated reviewer in your CI pipeline — on every pull request, it reads the diff, checks for bugs, security issues, missing tests, and convention violations, then posts its findings as a PR comment. Your human reviewers get a head start because the obvious issues are already flagged before they look.
Before deploying, tell Claude to read your project — migrations, environment variables, queue workers, scheduled tasks, caching, third-party integrations — and generate a deployment checklist that's specific to your app. Not a generic "did you run migrations?" list, but one that knows YOUR infrastructure and catches the things YOUR deploy can break.
Instead of writing a README from memory or copying a template, tell Claude to read your project and generate one that's actually accurate — real setup instructions from your config, real architecture from your directory structure, real API examples from your routes, and real prerequisites from your dependency files.