"Company CEO Itamar Friedman said the multi-agent approach provided in version 2.0 of the Qoda platform now makes it possible to take advantage of recall and memory to enable AI agents to understand and review code at a level that is comparable to a senior-level engineer. For example, a Qodo Code Review Benchmark 1.0 evaluates AI reviews against 580 defects across 100 real pull requests (PRs) from production repositories."
"Available on DevOps platforms from GitHub, GitLab, and Bitbucket, Qodo is specifically designed to enable DevOps teams to identify issues in code quality, an issue that is becoming more problematic as the amount of flawed code generated by AI coding tools continues to increase. In the absence of any ability to review that code using an AI tool, it won't be too long before DevOps engineers who are responsible for code quality are simply overwhelmed, said Friedman."
Qodo released a version 2.0 code review platform that uses multiple AI agents with recall and memory to analyze and review code at levels comparable to a senior engineer. A Qodo benchmark evaluating 580 defects across 100 real pull requests produced an F1 score of 60.1%, outperforming seven other platforms. The platform integrates with GitHub, GitLab, and Bitbucket to help DevOps teams detect code-quality issues caused increasingly by AI-generated flawed code. The shift of the DevOps bottleneck toward code review creates urgent need to augment engineers. A Futurum Group survey found 60% of organizations use AI for software, prioritizing AI Copilot tools (38%), AI agent development (37%), AI-assisted testing (37%), and DevOps investment (37%).
Read at DevOps.com
Unable to calculate read time
Collection
[
|
...
]