Large language models (LLMs) like ChatGPT, Gemini, and Claude are shaking up how we write software, but let’s be clear: they aren’t magic wands. For me, the problems I try and solve fall into three categories: 1. I know what I know 2. I know when I don't know 3. I don't know what I don't know. I've detailed these in my latest blog post on how I use AI as a senior engineer.
Using prisma on a project? Use ChatGPT to make schemas in seconds.
For example, if I want to create a new User and Organization table with a many-to-many relationship, I'd use the following prompt.
PrismJS Highlighted Shell Command
I'm using prisma with a node application.
Create for me a prisma schema for a postgres database use uuid's that
are generated by default that has the following entities.
User - name, email
Organization - name
Create a many to many relationship between user and organization and
include a role for this link. Roles can be owner (default), admin or user.
This will create a schema.prisma file
PrismJS Highlighted Shell Command
// schema.prisma
generator client {
provider = "prisma-client-js"
}
datasource db {
provider = "postgresql"
url = env("DATABASE_URL")
}
model User {
id String @id @default(uuid()) @db.Uuid
name String
email String @unique
userOrganizations UserOrganization[]
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
}
model Organization {
id String @id @default(uuid()) @db.Uuid
name String
userOrganizations UserOrganization[]
createdAt DateTime @default(now())
updatedAt DateTime @updatedAt
}
model UserOrganization {
userId String @db.Uuid
organizationId String @db.Uuid
role Role @default(OWNER)
user User @relation(fields: [userId], references: [id], onDelete: Cascade)
organization Organization @relation(fields: [organizationId], references: [id], onDelete: Cascade)
@@id([userId, organizationId])
}
enum Role {
OWNER
ADMIN
USER
}
Now you can go ahead and add this to your database.
The PM Repo is a repository of the best tools, frameworks, metrics, and resources to help everyone deliver their next great product.
What this week has in store
Spent some time working on my chatbot and created a supervisor to handle different types of requests. These requests were routed through a qwen LLM that I hosted on my kubernetes cluster. This week, I will expand upon that and bring in a few more agents to see how well the routing works.
See you next week!
Mark C Allen
1:1 Chat
Need a Different Perspective
Do you have a problem with your release process? Has Kubernetes got you down? Do you need an outsider's perspective on what's holding up your deployments? If you have 25 minutes, book a time with me.
