For a full stack developer, it is important to identify the accurate number of elements for data models, controllers, logic, flows and user experience definitions. This is a key decision for the system design.

Here we are presenting an easy and straightforward method to identify all the elements of a product story which would be define the design and all prompt based automated code generation.

We're highlighting a contrast between traditional approaches to data modeling and tools like FastBuilder.AI, which automate the process.

In a traditional approach, an architect spends considerable time analyzing system requirements from various documentation, iterating on the data model to ensure it meets both current and future needs. This requires deep domain knowledge, close collaboration with stakeholders, and constant adjustments as requirements evolve. It's an intensive process of design, testing, and refinement to ensure scalability, performance, and maintainability.

FastBuilder.AI, as we describe, takes a different approach by automating the data architecture based on a "product story." As this tool can truly generate a functional, optimized data model from such input instantly, it could significantly reduce the time and effort needed to get from concept to implementation. However, questions may arise about the flexibility, long-term maintainability, and customizability of the AI-generated architecture.

This could mean that for certain projects, architects might spend less time on initial design but more on fine-tuning, integrating, and overseeing automated models, shifting their role from creators to curators. The potential for speed is high, but there would still be a need for expert oversight to ensure the generated architecture aligns with the system's broader objectives.

Writing a product story

Let's write a product story for online document notarization and signature. A simple one line story is enough to demonstrate this.

A user uploads a document for notarization by the notary.

The story analyzer identifies the actor, asset, action, model and process from this sentence.

The analysis finds out the following AAAMP elements:

• Actor
• User
• Asset
• Document
• Action
• Upload
• Process
• Notarization
• Notary
• Model
• (In graph)

Let us improve the story

We shall add more feature in the story.

A user uploads a document for notarization by the notary. The notary notarizes the document and returns to the user.

The story analyzer finds out the extended set of AAAMP as in the image below.

How to build software with AAAMP?

1. Backend:
2. Database & storage for @Asset & @Actor
3. User, Document
4. Controller for @Action with @Process
5. Upload
6. Frontend
7. Login & Profile for @Actor
8. User
9. Form & API for @Action with  @Process
10. Upload, Notary, Notarization

Building prompt sets for generative software engineering

• Write mass coding prompts using the AAAMP variables
• Write data models for @Actor
• Write data models for @Asset with @Model
• Write controllers for @Action with @Process

Starter prompt sets (MIT License)

• NodeJS Mass Prompts for backend
• https://github.com/FastBuilderAI/NodeJS
• Angular Mass Prompts for frontend
• https://github.com/FastBuilderAI/angular
• More prompt-sets releasing soon
• Follow us at Github/FastBuilderAI

.

.