News
Amazon Q Developer Agent Gets More Autonomous
Amazon Web Services (AWS) has updated its "Q" AI developer agent to be more accurate and capable of making autonomous coding decisions.
Released in late spring, Q is a natural language AI assistant that's integrated into several AWS solutions. The developer-specific SKU is designed to help with application coding, testing, troubleshooting, upgrading and more. Q's developer agent feature works within an IDE to help developers add features or make changes to their code.
This week, AWS described an update to the Q developer agent that makes it more effective at managing developer workflows and accomplishing more complex tasks. Specifically, AWS has created a new text-based IDE called "textcode" that provides the Q developer agent a more intuitive workspace than a visual IDE.
"Textcode is designed to provide token-efficient text representations of code, code files, and code workspaces," AWS explained in a blog post Monday. "It allows LLMs to interact with a code base in a similar manner to how a developer interacts with it in a visual IDE. This framework offers structured and efficient environment within which it is easy for the agent to use tools, take actions, and evaluate its progress towards the completion of the assigned task."
The updated agent is also more capable of intelligently navigating its workspace. It can, for instance, open and close files, select and unselect chunks of code, find and replace code, and undo changes. It can also use logic to avoid getting stuck in unproductive loops.
"These tools allows the agent to navigate the workspace in order to identify and retain the critical pieces of information to solve your tasks while discarding superfluous code to not clog its context," said AWS.
The updated Q developer agent is measurably more performant than the original version. In SWE-bench benchmark tests, which measure an AI system's ability to solve real-world Python-based problems, the new version completed 51 percent more tasks that the original.
"The agent is continuously updated and improved to give you better performance," said AWS. "During the past months the ability of foundation models to drive agentic workflows and leverage large sets of tools to accomplish complex tasks has improved significantly. Guided by customer feedback, we have redesigned our agent to take advantage of these new abilities."