Introduction

FastBuilder is a platform and collection of tools for making structured knowledge graphs from a product story document for any kind of software development purpose, with focus on "actor", "asset" and "action" type of entities. We focus on identifying these AAAMP entities from a product story for instant software development.

Every document, or at least a sentence, is made up of one or more these AAAMP elements along with some decorative, like prepositions articles, etc, which are not that important at this time.

Document ==> Graph(Actor, Asset, Action, Model, Process)

Generally the subjects and objects of sentence, in terms of grammar, are actor or asset. But it is more complex than mapping parts of speech to AAAMP. We have trained a parser to discover AAAMP from documents. It works in a variety of human languages.

The document parser, a trained and pluggable PoS + NER language model, identifies all the actors, assets, actions, model and process as well as all the relationships among them.

Applications ✨

Knowledge graphs(K-graph in short from hereon) are primarily used for organizing data from multiple sources, and capture information about entities of interest. Although we go beyond that for applying K-graphs in various scenarios of content generation, content control and content exploration.

Applications in Content Generation for making software

A fully connected K-graph provides complete information about the nature of a data element.

Derived graph for A => D(A) = δG/δA 

   ; where A can be any element of graph. In this context, it is either actor, asset, action, model & process.

A D(A) based prompt can be an effective way to create a better prompt for prompt generation. As such a good prompt for generative AI system should have all the blocks and channels for a holistic content generation. Therefore a derived graph D(A) can be used to make a completely good prompt. Using this mechanism, the prompt creation can be automated as well. 

Here the prompt can be used for any type of generative tasks like text generation, or code generation, or image generation, or any other type of generation objective. In later section, we explain the mechanism to make prompt sets.

Approach

To generate the software from a story, there are a number of steps namely

1. Building the document as Product Story 
2. Analyzing the document to discover AAAMP
3. Developing the prompt for code generation
4. Running the promptest across the AAAMP
5. Code fine-tuning, Testing & Release.

FastBuilder works on the principle of AAAPM(Actor-Asset-Action-Process-Model). These entities are derived from the product story. Just enter the story in the storypad and click on the analysis button.

The prompt sets are written with these variables as following:

1. @Function,
2. @Actor,
3. @Asset,
4. @Action,
5. @Model,
6. @Process,
7. @Code

The @Function variable is synthesized from the "Gen" parameter of the promptset. The "Gen" can be one or more of AAAPM(Actor-Asset-Action-Process-Model).

Next: Quickstart