Amazon rolls out a genAI-powered inline chat function for Amazon Q Developer

Saving even a few keystrokes is worth quite a bit to enterprise developers, and to assist with that, Amazon Tuesday rolled out an updated version of its genAI-powered in-IDE chat capabilities that brings the AI-suggested code and documentation directly into the code editor, as opposed to having it appear in a separate window from which it then has to be cut and pasted into the program. It is available within the Visual Studio Code and JetBrains integrated development environments (IDEs).

“Amazon Q Developer announces an enhanced chat experience that allows you to seamlessly initiate chat within the inline coding experience,” said the brief Amazon announcement. “With this capability, you can select a section of code that you need assistance with and initiate chat within the editor to request actions such as ‘Optimize this code,’ ‘Add comments’ or ‘Write tests.’”

Amazon Q Developer is built on Amazon Bedrock, and inline chat is the first Amazon Q Developer capability powered by the latest version of Anthropic’s Claude 3.5 Sonnet, which launched on Oct. 22, Amazon said. 

Analysts are impressed

Jason Andersen, a VP and principal analyst for Moor Insights & Strategy, took note of the Anthropic reference in Amazon’s statement.

“Amazon selected a new version of Anthropic Sonnet, which is geared towards programming. I am guessing that the model switch was not just to enable inline features, but Amazon has some data that says the new model is more reliable than what they selected previously,” Andersen said. “But again, that is speculation. I would expect that Amazon may have something of a new acceptance rate at re:Invent in December.”

Overall, Andersen said that he was favorably impressed with what Amazon rolled out.

“The new inline chat capabilities are a significant usability improvement for the Q Developer platform. And while there are many other vendors out there attempting to do the same thing, the Q Developer team is bringing a couple of unique perspectives to the mix,” Andersen said. “The first is really homing in on making the experience more meaningful for the developer. Inline coding assistance allows you to see and effectively work with the AI in your code.

“Other assistants, including Q, had the chat on the side. So, while helpful, you were constantly in between windows, making it a bit clunky at times. The inline experience is more contextual, so it’s easier for devs to see what the AI is doing with respect to code that is already in place. I think it will lead to higher acceptance rates for code recommendations, which is a measure that the Amazon team is very focused on when measuring developer productivity improvement.”

Andersen also pointed to Amazon’s claims regarding easier and more accurate documentation, a longtime issue in the enterprise. 

“The Q Developer team often discusses the developer role across the entire development and software lifecycle, versus just coding,” Andersen said. “Showing how easy it is to add compelling documentation while you code is another example of that focus.”

Another analyst, Ritu Jyoti, the general manager for AI at IDC, pointed to Amazon’s support for agentic coding as significant, although it has both good and bad elements.

“Support for agentic coding is exciting, but as we all know, it is early days for agentic AI and there are quite a few challenges and concerns. Ensuring that multiple AI agents communicate and coordinate effectively can be complex. Miscommunication or lack of synchronization can lead to errors or inefficiencies,” Jyoti said. “Balancing the collaboration between AI agents and human developers can also be challenging. Ensuring that AI agents complement rather than replace human efforts is crucial for maintaining team morale and effectiveness.”

Jyoti also flagged the fact that many enterprises are experimenting with many AI packages simultaneously. Although overall desirable, such efforts can deliver “debugging complexity.”

“Debugging issues that arise from the interactions between multiple AI agents can be more complex than dealing with a single AI tool. This complexity requires advanced monitoring and diagnostic tools,” Jyoti said, adding that multiple AI agents handling sensitive data could also generate security and privacy issues.

How it can help developers

An AWS senior developer advocate, Jose Yapur, posted a blog describing why he thinks the changes will be especially helpful for developers, and his personal experience working with the new capabilities. 

“The chat interface not only generated code, but also provided explanatory context. I preferred to use inline suggestions when I knew what I was doing, and chat when I was learning something new. When fixing a bug, inline suggestions excel at generating new code, but do not easily allow me to update the existing code. Chat allows me to update existing code, but the response is provided in the chat window rather than being directly integrated into my code. This is where inline chat aims to improve the workflow,” Yapur wrote. “The AI-generated response is then seamlessly merged into my existing code, rather than requiring me to copy and paste from a separate chat window. I can easily review the suggested changes and accept, or decline, them with minimal effort. This new capability is ideal for editing an existing file to fix issues, optimize code, refactor code, add comments. And, it’s included in Amazon Q Developer’s expansive Free tier.”

Yapur also spoke of the tool’s documentation capabilities. 

“In the chat interface, I entered the prompt ‘Add documentation including descriptive comments throughout the code.’ Q Developer swiftly analyzed the code and generated appropriate documentation,” Yapur said. “Amazon Q Developer created a detailed comment block at the beginning of the script, including parameter descriptions and return value information. It also added inline comments throughout, explaining complex logic and calculations.”

And, Yapur added, inline chat smooths the road for busy developers.

“Whether it’s generating new features, refactoring existing code, or adding comprehensive documentation, inline chat streamlines the workflow, eliminating the need to switch between separate chat and editor windows,” he said.