Blab AI
Qodo Expands AI Code Review Platform to Support Multi-Repository Governance
Qodo, the enterprise AI code‑review platform formerly known as CodiumAI, announced a set of new features that extend its governance capabilities across multiple code repositories. The updates, released this week, add an AI agent that can review code changes spanning several repositories, a custom rules miner that discovers coding patterns from existing code and pull‑request history, and a portal that surfaces AI skills containing code‑review instructions, coding standards, and engineering best practices.
The platform’s latest version, 2.8, introduces a rules‑miner that scans a codebase’s historical behavior and pull‑request activity to generate structured, enforceable rules. These rules can be applied automatically during future pull‑request reviews, ensuring that new changes adhere to patterns that have proven effective in the past. In addition, Qodo’s new skill‑discovery feature identifies AI modules that embed code‑review guidance and best‑practice knowledge across multiple repositories. The skills are displayed in a central portal, allowing DevOps teams to manage and assess their impact on engineering workflows.
According to the company, the AI agent is built on graph technology that tracks relationships between code elements. "Whenever a pull request (PR) modifies a shared dependency, the agent reads the repositories affected to surface impact findings before the PR is merged," CEO Itamar Friedman said. The agent can surface potential issues such as function‑signature violations, API contract breaks, schema changes, and infrastructure drift. The feature is available in beta and is designed to let teams see how a change might adversely affect a microservice without requiring engineers to review every line of code.
Friedman explained that the shift in bottlenecks—from writing code to reviewing it—is a direct result of the increasing volume of AI‑generated code. "In the age of AI coding, the bottleneck that stymies DevOps teams has moved from writing code to reviewing it," he said. "As the volume of code being generated continues to increase, human developers are now able to keep pace with the rate of change," Friedman added. The company argues that its graph‑based approach allows both AI agents and human developers to focus on changes that could create issues before code is merged.
The platform’s goal, according to Qodo, is to help DevOps teams identify the tasks that consume the most time and to determine where AI agents can have the greatest impact on moving higher‑quality code into production faster. "The ultimate goal is to enable DevOps teams to start identifying the tasks and bottlenecks today that are consuming the most time to better identify when and where to apply AI agents in a way that has the most substantial impact on moving higher quality code into production environments as fast as possible," Friedman said.
Qodo also highlighted the challenge of ensuring that the AI agent reviewing code is not based on the same model that created the code. "At this juncture, it’s apparent that humans will not be able to review every line of code created using an AI tool. The only way to identify issues will be to rely more on AI agents to review code created by other AI agents. The challenge is making sure that the AI agent reviewing the code is not based on the same AI model used to create the code in the first place," the CEO noted. He added that future software engineering may evolve into an “AI factory”—a system of AI agents that must be orchestrated and supervised.
Qodo’s updates come as the company continues to position itself as a comprehensive solution for AI‑driven code review, quality, and SDLC governance. The platform already supports automated reviews on pull requests, bug detection, standards enforcement, and context‑aware feedback. With the new multi‑repository capabilities, Qodo aims to address the growing need for cross‑repo impact analysis in distributed development environments.
At present, the new features are in beta. Qodo has not announced a public release date or pricing for the expanded functionality. The company’s focus remains on refining the agentic review process and expanding its rule‑mining and skill‑discovery capabilities to support larger, more complex codebases.
The updates reinforce Qodo’s strategy of combining AI with graph‑based code analysis to provide scalable, consistent code‑review workflows. As AI‑generated code becomes more prevalent, tools that can automatically surface cross‑repository impacts and enforce best practices will likely become essential components of modern DevOps pipelines.
The platform’s latest version, 2.8, introduces a rules‑miner that scans a codebase’s historical behavior and pull‑request activity to generate structured, enforceable rules. These rules can be applied automatically during future pull‑request reviews, ensuring that new changes adhere to patterns that have proven effective in the past. In addition, Qodo’s new skill‑discovery feature identifies AI modules that embed code‑review guidance and best‑practice knowledge across multiple repositories. The skills are displayed in a central portal, allowing DevOps teams to manage and assess their impact on engineering workflows.
According to the company, the AI agent is built on graph technology that tracks relationships between code elements. "Whenever a pull request (PR) modifies a shared dependency, the agent reads the repositories affected to surface impact findings before the PR is merged," CEO Itamar Friedman said. The agent can surface potential issues such as function‑signature violations, API contract breaks, schema changes, and infrastructure drift. The feature is available in beta and is designed to let teams see how a change might adversely affect a microservice without requiring engineers to review every line of code.
Friedman explained that the shift in bottlenecks—from writing code to reviewing it—is a direct result of the increasing volume of AI‑generated code. "In the age of AI coding, the bottleneck that stymies DevOps teams has moved from writing code to reviewing it," he said. "As the volume of code being generated continues to increase, human developers are now able to keep pace with the rate of change," Friedman added. The company argues that its graph‑based approach allows both AI agents and human developers to focus on changes that could create issues before code is merged.
The platform’s goal, according to Qodo, is to help DevOps teams identify the tasks that consume the most time and to determine where AI agents can have the greatest impact on moving higher‑quality code into production faster. "The ultimate goal is to enable DevOps teams to start identifying the tasks and bottlenecks today that are consuming the most time to better identify when and where to apply AI agents in a way that has the most substantial impact on moving higher quality code into production environments as fast as possible," Friedman said.
Qodo also highlighted the challenge of ensuring that the AI agent reviewing code is not based on the same model that created the code. "At this juncture, it’s apparent that humans will not be able to review every line of code created using an AI tool. The only way to identify issues will be to rely more on AI agents to review code created by other AI agents. The challenge is making sure that the AI agent reviewing the code is not based on the same AI model used to create the code in the first place," the CEO noted. He added that future software engineering may evolve into an “AI factory”—a system of AI agents that must be orchestrated and supervised.
Qodo’s updates come as the company continues to position itself as a comprehensive solution for AI‑driven code review, quality, and SDLC governance. The platform already supports automated reviews on pull requests, bug detection, standards enforcement, and context‑aware feedback. With the new multi‑repository capabilities, Qodo aims to address the growing need for cross‑repo impact analysis in distributed development environments.
At present, the new features are in beta. Qodo has not announced a public release date or pricing for the expanded functionality. The company’s focus remains on refining the agentic review process and expanding its rule‑mining and skill‑discovery capabilities to support larger, more complex codebases.
The updates reinforce Qodo’s strategy of combining AI with graph‑based code analysis to provide scalable, consistent code‑review workflows. As AI‑generated code becomes more prevalent, tools that can automatically surface cross‑repository impacts and enforce best practices will likely become essential components of modern DevOps pipelines.
