How NRG holds one review standard across code written by engineers and code written by agents
CodeAnt gives our engineering teams faster, AI-based feedback and increases confidence in the quality of the code produced by both engineers and agents.
Biswajit Barman
Solutions Architect, NRG(Fortune 100)
NRG is a Fortune 500 energy company with over $30B in annual revenue and a market cap around $30B. It powers homes and businesses across North America under Reliant, Direct Energy, Green Mountain Energy, and Vivint, with roughly 15,000 employees. Engineering runs on Azure DevOps alongside other source control platforms.
CHALLENGE
At this scale, review quality is an operational risk.
NRG's software organization matches the size of the company. When a review process fails quietly at that volume, it does not produce an incident report. It produces a pattern.
WHY CODEANT
A tool in a separate dashboard is a tool nobody opens on a Friday afternoon.
NRG wanted the best code reviews available, working natively inside Azure DevOps and the rest of their stack. Not a bolt on. Reviews that show up where the engineer already is, catch what a human reviewer misses at the end of a long week, and hold the same line whether the code was written by an engineer or generated by an agent.
That last part matters more every quarter. NRG is shipping AI generated code at volume, like everyone else. The reviewer is now the control point, and a reviewer that has learned from real attacks is a different instrument than one running a rule pack.
WHAT WE RAN
Native review inside Azure DevOps and their other source control platforms, applying the same standard to human and agent authored code.
WHAT CHANGED
