Qodo launches Codex plugin to add org context to AI code review

The plugin uses OpenAI models, including GPT-6 Astra, to gather engineering knowledge. It operates by retrieving relevant codebase rules and pull request history before Codex writes code. After changes are made, Qodo’s Agentic Toolbox reviews them and returns findings to Codex within the same session, prior to the developer opening a pull request. This workflow aims to automate the handoff between coding and independent review, allowing agents to account for dependencies across different Git providers and services connected via Kafka.

Qodo’s AI Developer Relations Lead, Nnenna Ndukwe, notes that developers are using this setup to build features and tackle technical debt. Friedman envisions a future where coding and review agents collaborate, surfacing only unresolved issues for human review. He also highlights the potential of OpenAI’s Decisions API to select specific rules for checking, making the process faster and cheaper than relying on language models for every decision.