AI code review
The Metabob advantage
Metabob uses a combination of graph-attention neural networks (GNNs) and generative AI to improve software performance and security.
With this, Metabob can detect problems that aren't detected by traditional, rules-based, static code analysis tools such as SonarQube. The detected problems range from race conditions and memory leaks to unhandled edge cases.
GNNs and BERTopic
Metabob is an ensemble AI system for classifying, identifying and explaining non-deterministic faults within source code. BERTopic based topic modeling is used to build seed data sets. For doing so, the underlying reasons behind particular classes of code changes are collected, extracted from the surrounding documentation behind each code change.
This allows to conduct supervised training of a classifier using an extended version of the Abstract Syntax Tree (AST). This is parsed from the source code and used as the input vectors to a GNN. The fault class, as determined by BERTopic, is used as the output class per node in the GNN.
Generative AI
Metabob then generates explanations and code suggestions for fixes via a language model. These are built on a context vector from the topic labels, the source code, and portions of the online documentation, docstrings, headers, and other non-local information (readme’s, etc.). This results in simple explanations of the underlying issue behind a particular code change.
For Developers
Analyze code right in your IDE
Detect coding errors to prevent software bugs and get recommendations for improving code quality before further stages of development.
Metabob integrates seamlessly into your development environment with an easy-to-use VSCode plugin.
Don’t use VSCode? No problem
Metabob provides a CLI tool that can be integrated into any development environment.
Seamlessly Integrate Metabob’s AI with your DevOps Operation. Metabob offers an open-source CLI tool to analyze and refactor code through your command line.
AI code review outperforms
traditional static code analysis tools
After analyzing the whole codebase, Metabob uses generative AI to facilitate code review and improve software security
Increased developer productivity
Higher detection rate of critical errors
Error type:
App unable to start new threads after run period
40
Error type:
Data is overrepresented in certain batches
2.5
Error type:
App using 100% available CPU on certain setups