Gemini Code Assist, Google’s AI coding assistant, gets ‘agentic’ abilities

Gemini Code Assist, Google’s AI coding assistant, is gaining new “agentic” capabilities in preview.

During its Cloud Next conference on Wednesday, Google said Code Assist can now deploy new AI “agents” that can take multiple steps to accomplish complex programming tasks. These agents can create applications from product specifications in Google Docs, for example, or perform code transformations from one language to another. Code Assist is now available in Android Studio in addition to other coding environments.

Code Assist’s upgrades are likely in response to competitive pressure from rivals such as GitHub Copilot, Cursor, and Cognition Labs, the creator of the viral programming tool Devin. The AI coding assistant market grows fiercer by the month, and there’s a lot of money in it. Considering the tech’s productivity-boosting potential, that’s not totally surprising.

Code Assist’s agents, which can be managed from a new Gemini Code Assist Kanban board, can generate work plans and report step-by-step progress on job requests. Beyond generating software and migrating code, the agents can implement new app features, execute code reviews, and generate unit tests and documentation, the company claims.

However, it’s unclear just how well Code Assist can do all this. Even the best code-generating AI today tends to introduce security vulnerabilities and bugs, studies have found, owing to weaknesses in areas like the ability to understand programming logic. One recent evaluation of Devin found that it completed just three out of 20 tasks successfully.

So if you tap Code Assist to create or refactor an app for you, it couldn’t hurt to review the code yourself just to be safe.