Harness Launches AI Code Review for Software Development Teams

In September 2026, Harness recently launched Agent-Ready Harness Code Repository and AI Code Review, which are aimed at software teams using AI coding agents. The new repository and review tools are being introduced as a linked system. Harness states that code generated by AI agents is changing the volume and pace of software development, putting pressure on older source code management and review processes built around human developers opening and discussing pull requests over longer periods.

At the center of the launch is a code repository that is designed for large spikes in commits and pull requests. Harness said the system has been tested to handle thousands of pull requests and commits opened at the same time while maintaining search, history and diff functions across repositories of different sizes and with very large numbers of branches.

Another part of the release focuses on access control for AI agents. Agents can inherit permissions from the human users who trigger them, while developers can narrow those permissions to particular repositories, branches, or environments. The setup also supports role-based access control and Open Policy Agent policies to enforce boundaries before code is merged.

These tools are also available through the command line using the Harness MCP and CLI. Harness said this allows users to manage the full pull request process without opening a browser, including finding reviews by an author's email address, viewing open pull requests across repositories, and creating or resolving comment threads. AI agents can also use CLI commands to carry out repository and review actions in headless mode, according to the company.

Impact on the AI Market

The AI Code Review product is intended to reduce the burden on human reviewers as code volumes rise. Teams can now decide which AI checks are mandatory and apply them at account or project level, with failed required checks blocking a merge. The review process also changes how code differences are presented. Instead of grouping changes by file, the system groups them by risk, with the aim of highlighting changes that alter software behavior ahead of lower-priority modifications such as file renames or dependency updates.

Harness further stated that its review tool also offers what it describes as one-click remediation. Feedback is framed around the implications of a code change, while suggested reviewers and labels are added before a pull request is opened. If the feedback is accepted, changes can then be merged with a single click, the company said. Both are now part of the outer loop that the Harness Software Delivery Agent runs end-to-end, from commit to production, under one policy engine.

Impact on the Artificial Intelligence of Things (AIoT) Market

The global artificial intelligence of things (AIoT) market size accounted for USD 225.89 million in 2025 and is predicted to increase from USD 297.60 million in 2026 to approximately USD 3,248.22 million by 2035, expanding at a CAGR of 30.55% from 2026 to 2035.

According to Precedence Research, the market is rapidly evolving as organizations seek to harness real-time intelligence from connected devices. The Internet of Things and artificial intelligence are combined to create AIoT, whereby AI algorithms evaluate data from networked devices to facilitate quicker, more intelligent, and self-governing decision-making. Businesses can use predictive maintenance techniques to increase asset utilization, lower operating costs, and boost productivity thanks to this integration. The increasing need for automation, real-time analytics, and smart infrastructure is fueling the expansion of AIoT use in the manufacturing, healthcare, transportation, retail, and energy sectors.

Artificial intelligence also plays a crucial role in connected devices like IoT, enabling intelligent automation and real-time decision-making. By integrating AI into IoT systems, businesses can glean useful insights from massive volumes of sensor-generated data. Predictive maintenance is made possible through AI, enabling autonomous control and enhancing the operational efficiency of IoT. Advanced features like pattern recognition, anomaly detection, facial/object recognition, and natural language interaction are also being made possible by AI, which allows IoT devices to go beyond simple data collection.

Impact on the Artificial Intelligence Software Market

The global artificial intelligence (AI) software market size was calculated at USD 257.37 billion in 2025 and is predicted to increase from USD 316.50 billion in 2026 to approximately USD 1,640.51 billion by 2035, expanding at a CAGR of 20.35% from 2026 to 2035.

According to Precedence Research, the market growth is driven by high demand for automation through intelligence, investment in AI technologies, and rising implementation of advanced software solutions in industries such as healthcare, BFSI, retail, manufacturing, and IT. The advent of agentic AI, multimodal AI models, and AI copilots is expected to accelerate the market growth rate globally.

Artificial intelligence (AI) also plays a transformative role in modern software solutions by enabling systems to move beyond traditional rule-based operations toward intelligent automation, predictive decision-making, and adaptive learning. AI-powered software integrates technologies such as machine learning (ML), deep learning, natural language processing (NLP), computer vision, and generative AI, helping to automate complex tasks, analyze large volumes of data, and improve overall operational efficiency across various industries.

Expert Opinion

"Software delivery is going through its biggest shift since the move to the cloud, and the systems we all built our workflows around were designed for a different scale and a different kind of user," said Jyoti Bansal, CEO and co-founder of Harness. "You do not solve that by adding AI features to a repository designed fifteen years ago. The entire SDLC has to become autonomous, which means the repository, the review, the pipeline, and the governance must all work as one system."