Turning ChatGPT into a Product Manager (and Tech Assistant)

Initial Prompt:

You are a Product Manager in charge of launching a Meat Delivery e-commerce application. Develop a 3 months roadmap to create an MVP website/iOS app. Divide this time into sprints and create a table to have tasks prioritized for each sprint. For now, keep it simple, you have 3 teams. One for backend service one for Frontend and iOS app and one for Infrastructure and DevOps.

Prompt: Generate granular tasks for all teams in Sprint 1, organized by the team in a tabular format, including time estimates for each task:

Prompt: How many microservices should we have?

Prompt: Show swagger spec for each:

Here are Swagger (OpenAPI 3.0) specifications for each microservice mentioned in the previous response. Please note that the provided specs are simplified and should be expanded based on your application requirements.

1. User Service:

openapi: 3.0.0
info:
  title: User Service API
  description: Handles user registration, login, profile management, and authentication.
  version: 1.0.0

paths:
  /register:
    post:
      summary: Register a new user
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                email:
                  type: string
                  format: email
                password:
                  type: string
                  minLength: 8
              required:
                - email
                - password
      responses:
        '201':
          description: User created successfully
        '400':
          description: Invalid request data

  /login:
    post:
      summary: Login a user
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                email:
                  type: string
                  format: email
                password:
                  type: string
                  minLength: 8
              required:
                - email
                - password
      responses:
        '200':
          description: User logged in successfully
          content:
            application/json:
              schema:
                type: object
                properties:
                  token:
                    type: string
                    description: JWT token
        '401':
          description: Invalid email or password

  /users/{userId}:
    put:
      summary: Update user profile
      security:
        - bearerAuth: []
      parameters:
        - in: path
          name: userId
          required: true
          schema:
            type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                email:
                  type: string
                  format: email
                password:
                  type: string
                  minLength: 8
      responses:
        '200':
          description: User updated successfully
        '400':
          description: Invalid request data
        '401':
          description: Unauthorized
        '404':
          description: User not found

    delete:
      summary: Delete user account
      security:
        - bearerAuth: []
      parameters:
        - in: path
          name: userId
          required: true
          schema:
            type: string
      responses:
        '204':
          description: User deleted successfully
        '401':
          description: Unauthorized
        '404':
          description: User not found

components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
-----truncated-----

1. Product Service:

openapi: 3.0.0
info:
  title: Product Service API
  description: Manages product information, including search, filter, and categorization.
  version: 1.0.0

paths:
  /products:
    get:
      summary: Retrieve a list of products
      parameters:
        - in: query
          name: search
          schema:
            type: string
        - in: query
          name: category
          schema:
            type: string
      responses:
        '200':
          description:
--- truncated-----

Prompt: Provide a sample Terraform to create this cluster

Here's a sample Terraform configuration for creating a cluster on AWS using Elastic Kubernetes Service (EKS). This example sets up a VPC, EKS cluster, and worker nodes.

Please note that this is a simple example, and your specific infrastructure requirements may require additional configuration.

hclCopy codeprovider "aws" {
  region = "us-west-2"
}

locals {
  cluster_name = "meat-delivery-ecommerce"
}

resource "aws_vpc" "this" {
  cidr_block = "10.0.0.0/16"

  tags = {
    Terraform = "true"
    Kubernetes = "true"
    Name = local.cluster_name
  }
}

module "vpc" {
  source = "terraform-aws-modules/vpc/aws"

  name = local.cluster_name
  cidr = "10.0.0.0/16"

  azs             = ["us-west-2a", "us-west-2b", "us-west-2c"]
  private_subnets = ["10.0.1.0/24", "10.0.2.0/24", "10.0.3.0/24"]
  public_subnets  = ["10.0.101.0/24", "10.0.102.0/24", "10.0.103.0/24"]

  tags = {
    Terraform = "true"
    Kubernetes = "true"
  }
}

resource "aws_security_group" "worker_group_mgmt_one" {
  name_prefix = "worker_group_mgmt_one"
  description = "EKS worker group management one"
  vpc_id      = aws_vpc.this.id

  tags = {
    Terraform = "true"
    Kubernetes = "true"
  }
}

module "eks" {
  source = "terraform-aws-modules/eks/aws"

  cluster_name = local.cluster_name
  subnets      = module.vpc.private_subnets

  tags = {
    Terraform = "true"
    Kubernetes = "true"
  }

  vpc_id = aws_vpc.this.id

  kubeconfig_aws_authenticator_command = "aws"
  kubeconfig_aws_authenticator_command_args = [
    "eks",
    "update-kubeconfig",
    "--region",
    "us-west-2",
    "--name",
  ]

  kubeconfig_aws_authenticator_additional_args = ["--role-arn", aws_iam_role.eks_cluster.arn]
  kubeconfig_name                              = local.cluster_name

  eks_cluster_version = "1.21"

  node_groups = {
    main = {
      desired_capacity = 2
      max_capacity     = 10
      min_capacity     = 1

      instance_type = "t3.small"
      additional_tags = {
        Terraform = "true"
        Kubernetes = "true"
      }
    }
  }

  manage_aws_auth = true
}

output "aws_vpc_id" {
  value = aws_vpc.this.id
}

Before running this Terraform configuration, make sure to install Terraform and configure your AWS credentials. Once that's done, you can initialize and apply the configuration with the following commands:

terraform init
terraform apply

This configuration sets up a VPC, EKS cluster, and worker nodes using the t3.small instance type. Adjust the settings as necessary to fit your requirements.

Prompt: Create a helm chart to deploy all the service

To create a Helm chart for deploying your services, follow these steps:

1. Install Helm CLI (if not already installed): helm.sh/docs/intro/install

2. Create a new Helm chart:

    helm create meat-delivery-ecommerce
   

   This will create a new directory named meat-delivery-ecommerce with the basic structure of a Helm chart.

3. Update the chart configuration:

   In the meat-delivery-ecommerce directory, open the Chart.yaml file and update the metadata as needed, such as the chart name, description, and version.

    apiVersion: v2
    name: meat-delivery-ecommerce
    description: A Helm chart for the Meat Delivery Ecommerce application
    type: application
    version: 0.1.0
    appVersion: 1.0.0
   

4. Configure the services:

   In the meat-delivery-ecommerce/templates directory, you will need to create new YAML files for each microservice, such as user-service.yaml, product-service.yaml, and any other services you have. For simplicity, I'll show an example of the user-service.yaml:

    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: user-service
    spec:
      replicas: 1
      selector:
        matchLabels:
          app: user-service
      template:
        metadata:
          labels:
            app: user-service
        spec:
          containers:
            - name: user-service
              image: <YOUR_USER_SERVICE_IMAGE>
              ports:
                - containerPort: 8080
    ---
    apiVersion: v1
    kind: Service
    metadata:
      name: user-service
    spec:
      type: ClusterIP
      selector:
        app: user-service
      ports:
        - protocol: TCP
          port: 80
          targetPort: 8080
   

   Replace <YOUR_USER_SERVICE_IMAGE> with the Docker image for your user service. Create similar files for other services, and update the container images, ports, and other settings as needed.

5. Customize values:

   Edit the meat-delivery-ecommerce/values.yaml file to add any custom values or settings for your services.

6. Package the chart:

   In the parent directory containing meat-delivery-ecommerce, run the following command to package the chart into a .tgz archive:

    helm package meat-delivery-ecommerce
   

7. Deploy the chart:

   After packaging the chart, you can deploy it to your Kubernetes cluster with the following command:

    helm install meat-delivery-ecommerce ./meat-delivery-ecommerce-0.1.0.tgz
   

   Replace meat-delivery-ecommerce-0.1.0.tgz with the name of the packaged chart generated in step 6.

Prompt: Should I replace the Product Manager with you?

As an AI language model, I'm here to help and provide information, but I'm not a direct replacement for a human Product Manager. Product Managers possess a unique set of skills, including interpersonal communication, leadership, and decision-making, which are crucial to the success of a project. While I can help with providing information and suggestions, I cannot replace the human touch and real-world experience that a Product Manager brings to the table. It's essential to have a well-rounded team, including both AI tools and skilled professionals, to achieve the best results.

Note

Everything is generated using Chat GPT-4 and the cover image is generated using Dall. E
None of this is tested.