OpenAI published a customer story on 2026-11-02 about Qodo, a company that builds AI tools for code review and software quality, and its plugin in the Codex marketplace (OpenAI). The plugin gives Codex access to codebase knowledge, organizational rules and independent review through Qodo’s Agentic Toolbox (OpenAI).
Qodo uses OpenAI models including GPT‑6 Astra to gather engineering knowledge, review code and monitor software quality (OpenAI). Its Codex plugin brings that context and review into developers’ coding sessions (OpenAI).
Key Facts
| Item | Detail | Source |
|---|---|---|
| Product | Qodo plugin in the Codex marketplace | OpenAI |
| Models | Qodo uses OpenAI models including GPT‑6 Astra | OpenAI |
| Before coding | Codex can retrieve codebase rules and pull request history and patterns | OpenAI |
| After coding | Qodo reviews the changes and returns findings in the same session | OpenAI |
| Cross-repository scope | Covers repositories on different Git providers and services connected through Kafka | OpenAI |
Timeline
- 2026-11-02: OpenAI published its account of Qodo’s Codex plugin (OpenAI).
Details (as Reported)
Qodo co-founder and CEO Itamar Friedman calls the company’s tooling “the coding agent’s best friend” (OpenAI). He describes customer environments that can span 10,000 or more repositories, where a local code change can break a downstream service even if it looks correct on its own (OpenAI). The plugin was built to address that problem (OpenAI).
With context from the plugin, Codex can account for dependencies across repositories, including those hosted by different Git providers or services connected through Kafka (OpenAI). Before Codex writes code, it can use the plugin to retrieve the relevant codebase rules and pull request history and patterns (OpenAI). After the changes are made, Qodo reviews them and returns its findings directly to Codex in the same session, before the developer opens a pull request (OpenAI).
Nnenna Ndukwe, Qodo’s AI Developer Relations Lead, sees developers using the workflow to build features and tackle technical debt with GPT‑6 models in Codex (OpenAI). Internally at Qodo, she has used GPT‑6 Astra’s Extra High and Ultra effort settings in her own automated development workflows and in knowledge work (OpenAI). She schedules Codex to report on her weekly work, to research conversations about agentic engineering on social platforms, and to suggest agent skills to create or refine (OpenAI).
Friedman describes coding and review agents as “yin and yang”: one creates code and the other challenges it (OpenAI). He sees an opportunity to use OpenAI’s recently launched Decisions API to choose which rules and agent skills apply at each stage of development (OpenAI). As an example, he cites the API selecting which of 200 rules need checking before a language model reasons through the relevant ones (OpenAI).
What Is Not Yet Confirmed
- Friedman’s stated vision is for agents to discuss findings and “surface only what they don’t accept” for human review (OpenAI).
- Friedman describes the Decisions API as an opportunity for Qodo, not as a feature already in use (OpenAI).
- Friedman describes a software factory that customers could assemble and own, combining coding and review agents (OpenAI).