Multi-language program and data flow analysis using LLM

A computer system for analyzing program and data flows in a software system of an enterprise, wherein the software system comprises code written in multiple programming languages, the computer system comprising:

• a code repository storing source code of the enterprise, the source code including code written in at least two different languages;
• a prompt library storing a plurality of predefined prompts tailored to different programming languages;
• a backend computer system comprising a generative large language model (LLM) configured to process the source code using selected prompts from the prompt library to generate a plurality of labeled graph nodes, wherein each labeled graph node represents a functional component of the software system and comprises:
• a node type;
• a node name;
• and
• for each functional component of the software system dependent on one or more other labeled graph nodes, dependency information for the node corresponding to the functional component, wherein the dependency information identifies the one or more other labeled graph nodes on which the functional component depends;
• and
• a graph construction computer system in communication with the backend computer system, the graph construction computer system configured to:
• generate a directed graph based on the plurality of labeled graph nodes, wherein each labeled graph node is represented as a node in the directed graph and directed edges between the nodes are established based on the dependency information;
• and
• provide, via a front-end interface, a visual representation of the directed graph to a user, thereby enabling analysis of program and data flows across the software system independent of the programming languages in which the code of the software system is written.

A computer-implemented method for analyzing program and data flows in a software system of an enterprise, wherein the software system comprises code written in multiple programming languages, the method comprising:

• processing, by a generative large language model (LLM) executed on a backend computer system, source code of the software system using selected prompts from a prompt library, wherein each selected prompt is tailored to a respective programming language of the source code, to generate a plurality of labeled graph nodes, each labeled graph node representing a functional component of the software system and comprising:
• a node type;
• a node name;
• and
• dependency information identifying one or more other labeled graph nodes on which the functional component depends;
• constructing, by a graph construction computer system, a directed graph comprising the plurality of labeled graph nodes and directed edges established based on the dependency information;
• storing the directed graph in a graph database configured to support traversal queries over the directed graph;
• executing, by a graph processing engine in communication with the graph database, a graph traversal query on the directed graph to identify one or more of:
• cross-language dependencies between functional components,
• an impact analysis of changes to a functional component, or
• a security vulnerability associated with a functional component;
• and
• providing, via a user interface, a query result comprising a visualization of a portion of the directed graph responsive to the graph traversal query.

A computer system for analyzing program and data flows in a software system of an enterprise, wherein the software system comprises code written in multiple programming languages, the computer system comprising:

• a backend computer system comprising at least one processor and memory storing instructions that, when executed by the processor, cause the processor to implement:
• a generative large language model (LLM) configured to process source code of the software system using selected prompts from a prompt library, wherein each selected prompt is tailored to a respective programming language of the source code, to generate a plurality of labeled graph nodes, each labeled graph node representing a functional component of the software system and comprising:
• a node type;
• a node name;
• and
• dependency information identifying one or more other labeled graph nodes on which the functional component depends;
• a graph construction component configured to construct a directed graph comprising the plurality of labeled graph nodes and directed edges established based on the dependency information;
• and
• a graph processing engine configured to execute a graph traversal query on the directed graph to identify one or more of:
• cross-language dependencies between functional components, an impact analysis of changes to a functional component, or a security vulnerability associated with a functional component;
• a graph database configured to store the directed graph and support traversal queries over the directed graph;
• and
• a frontend visualization component implemented by at least one processor and configured to generate, and provide via a display device, a visualization of a portion of the directed graph responsive to the graph traversal query.