GitHub's new 'Agent Mode' feature lets AI take the reins for developers
The new GitHub feature will be able to complete entire requests and automatically fix errors
GitHub has launched a new agentic AI tool for developers, dubbed ‘Agent Mode’, alongside a raft of updates to the Copilot service.
Agent Mode enables Copilot to iterate on its own outputs and complete entire user requests in one go, thereby automating broader aspects of the development process. It can also automatically fix errors, suggest terminal commands, and assess run-time errors.
Copilot will now iterate repeatedly on its output until all the necessary subtasks of a prompt are complete, GitHub CEO Thomas Dohmke said, and will infer additional tasks that were not specified but are necessary to fulfill the primary request.
The new agentic capabilities will improve Copilot Workspace, allowing collaborative users to leverage a system of sub-agents in the platform to improve efficiency when generating plans, implementing code, or fixing errors.
“Agent mode will change the way developers work in their editor; and as such, we will bring it to all IDEs that Copilot supports,” Dohmke said.
Another feature introduced to Copilot is the ‘Next Edit’ function, which can automatically identify and suggest edits of a user’s previous changes. Accessed by pressing tab, users will be able to browse suggestions throughout any open file.
Vision for Copilot was also unveiled, which will allow users to create a mock-up piece of code from a snippet of content, such as a shorter portion of code, a screenshot, or an image. With this, Copilot can generate the UI, alt text, and code.
GitHub referred to its forward-looking plan, ‘Project Padawan,’ through which developers will be able to assign entire issues to Copilot, let it complete the task, and then evaluate and review the results.
The next step in AI code assistance
This announcement could mark yet another significant step in AI-based code assistance, which has been gaining huge popularity as a use case amongst developers and businesses. Google recently revealed that over 25% of its proprietary code is now AI-generated, for example.
GitHub has been at the center of the AI coding conversation for a while, having released GitHub Copilot Enterprise in early 2024, which it followed up with the release of GitHub Copilot Workspace a couple of months later.
GitHub touts the benefits of its tools, claiming that GitHub Autofix fixes software vulnerabilities at more than three times the speed of manual fixes, and at more than seven times the speed for cross-site scripting vulnerabilities.
There have been questions raised about the effectiveness of AI coding tools, though, with one study finding that developer performance has largely remained unchanged despite the use of coding tools.
RELATED WHITEPAPER
GitHub’s own research paints a more positive picture, however. Based on a survey of 2,000 software engineers and developers, the firm found that many reported several benefits related to AI coding tools.
Many said the tools improved code quality, helped deliver more secure software, improved test case generation, and allowed for the faster adoption of new languages.
These tools also enable better time utilization, with 47% of respondents in the US and Germany using the time they saved for collaboration and system design.
MORE FROM ITPRO
- Can AI code generation really replace human developers?
- The world's 'first AI software engineer' isn't living up to expectations
- AWS CEO Matt Garman thinks AI coding tools could herald the end of the developer as we know it
-
Cisco sounds alarm over new Russian malware campaign hitting firms in US and EuropeNews UAT-11795 is weaponizing legitimate software such as WebEx and Zoom to dupe victims
-
Why doesn't more data produce better results?ITPro Podcast Riverbed CIO Fernando Castanheira talks about data and how businesses can use it better
-
‘The challenge now is making sure the next generation develops those same foundations before relying too heavily on AI’: Devs are swerving fundamental skills like Git and Agile because of AI – but there’s a good reasonNews O'Reilly has recorded a massive fall in programming fundamentals courses, but that’s not to suggest devs aren’t learning key skills
-
‘The biggest barrier to growth is not access to technology, it is access to the right people’: Demand for developers with AI skills has surged 597% – but enterprises are still struggling to find the right talentNews Hiring is shifting away from traditional software development toward specialized roles to integrate, govern, and scale AI systems
-
Enterprises are shipping so much AI-generated code they can't control or secure itNews As AI coding becomes commonplace, organizations are struggling to control what they are shipping
-
Why is Windows 11 so disliked by programmers – and can Microsoft do anything to change things?Windows isn't the most useful OS in the eyes of developers, with programmers preferring macOS or Linux. But is its bad reputation uncalled for?
-
AI might help speed up software development, but 81% of devs now spend more time reviewing code – and it’s creating an ‘invisible work’ trend that’s pushing teams to the limit
News While AI is improving productivity and efficiency, many developers are caught up in a vicious cycle of code reviews and bug hunting
-
Everything you need to know about the GitHub Copilot pricing changesNews GitHub Copilot pricing changes mean users will be charged based on consumption, rather than a set number of credits
-
Developers are slacking on AI-generated code safety – here's why it could come back to haunt themNews While organizations are aware of the risks, many are spending little time or effort on tracking artifact versions, origins, and security attestations
-
Four things you need to know about GitHub's AI model training policy – including how to opt outNews Users of certain GitHub Copilot plans will have interaction data used to train AI models, but can opt out
