Qodo builds AI tools for code review and software quality, giving coding agents the organizational knowledge they need to understand the code they change. Co-founder and CEO Itamar Friedman describes it as “the coding agent’s best friend.” Qodo uses OpenAI models including GPT-6 Astra to gather engineering knowledge, review code, and monitor software quality, and its Codex plugin brings that context and review into developers’ coding sessions.

The company targets customer environments that can span 10,000 or more repositories, where a local change can break a downstream service even if it looks correct on its own. Qodo built a plugin in the Codex marketplace that gives Codex access to codebase knowledge, organizational rules, and independent review through Qodo‘s Agentic Toolbox. With that context, Codex can account for dependencies across repositories, including repositories hosted by different Git providers or services connected through Kafka. Qodo makes the connection and helps Codex look at the software as a whole and not miss P0 bugs.

Before Codex starts writing code, the plugin can retrieve relevant codebase rules and pull request history and patterns. After Codex makes changes, Qodo reviews them and returns findings directly to Codex in the same session, before the developer opens a pull request. Qodo‘s AI Developer Relations Lead, Nnenna Ndukwe, sees developers using this workflow to build features and tackle technical debt with GPT-6 models in Codex, automating the handoff between Codex‘s coding work and Qodo‘s independent review.

Friedman describes coding and review agents as “yin and yang”: one creates code, the other challenges it. Each role needs its own setup and context and may involve multiple agents. His vision is for agents to discuss findings and surface only what they do not accept for human review, with developers acting as planners and reviewers who can inspect unresolved issues alongside the agents’ discussion, context, and prior developer decisions. Friedman says that is how trust is created, and Ndukwe says it makes the process more efficient and lets people leverage the best parts of their expertise.

Internally, Ndukwe has been using GPT-6 Astra‘s Extra High and Ultra effort settings in automated development workflows and knowledge work. She schedules Codex to report on what she accomplished during the week and where she could focus or improve next, uses it to research conversations about agentic engineering on social platforms and suggest developer content ideas, and schedules it to analyze her code changes and suggest agent skills to create or refine.

Qodo also sees an opportunity in OpenAI’s Decisions API to choose which rules and agent skills apply at each stage of development, rather than relying on language models for every decision. Friedman cites an example where the Decisions API could select which of 200 rules need checking before a language model reasons through the relevant ones, making selection faster and cheaper while improving review quality. He calls it an immense opportunity to bring more trust to the process.

Qodo‘s approach combines AI with traditional software engineering and scripting: company knowledge guides coding agents, independent review checks their work, and human expertise resolves the remaining questions. Friedman describes this as the foundation of a software factory, a system customers could assemble and own, bringing coding and review agents together with an understanding of how software changes in production. With OpenAI, Qodo is building a future where coding agents put more of a company’s experience to work and developers focus their judgment where it matters most.