Gitar, a startup that uses agents to protect code, emerges from stealth with $9 million

With the advent of “vibe coding,” AI agents are unleashing massive amounts of code on businesses that many businesses struggle to manage. This sudden flood is called “code overload.” The report shows that code generated by AI can introduce significant problems in the codebase (including bugs and other quality issues), which must be fixed by senior engineers before the code can be “shipped” to market.

Now, a new company is trying to solve this problem using the same tool that created this problem: AI.

Gitar, a startup founded by Intel Labs, Google and Uber veteran Ali-Reza Adl-Tamatabai, emerged from stealth on Wednesday with a $9 million funding round led by Venrock with participation from Sierra Ventures.

Two-year-old Gitar sells subscription access to its platform. The platform deploys AI agents that perform various code quality operations, such as code reviews and managing continuous integration workflows. A continuous integration workflow is an automated process that regularly merges and tests code changes to keep the codebase stable and up-to-date. The platform enables engineering teams to create their own agents to perform security and maintenance operations on their behalf.

AI-generated code means “reviewing more code, writing more tests, and diagnosing more CI failures,” CEO Adl-Tabashi told TechCrunch. What Gitar does is “code validation,” he said, a way to make sure what’s being built within an enterprise is ready for prime time. “Generation produces code, and validation makes code trustworthy. Gitar is a workflow agent that owns that process and orchestrates review, testing, and diagnostics end-to-end,” he added.

Adl-Tabashibai believes that automation will play a more comprehensive role in software development in the future. “Currently, code shipped to production includes human reviews, and there’s a good reason for that, right? We want to make sure there’s nothing we’ve overlooked, so we have humans checking to make sure we don’t ship anything bad.”

His vision is that human code reviews will become a minimal part of the process, and companies will instead trust Gitar’s platform to handle those tasks and ship faster. “We have validation agents that can automatically verify that the code is safe to ship, and humans are only involved in exceptional cases,” Adl-Tabatabai claimed.

There are many other companies already working in the automated code review space, but Gitar hopes to differentiate itself by specializing in this problem. “Most of the market chased (code) generation. We didn’t,” Adol Tabatabai said. “Gitar is built around what happens after code is written.”

The new funding will be used to hire Gitar’s entire engineering and product team, and San Mateo will focus on developing systems that can deliver services at scale.