DEVOPSdigest

Amazon Web Services, Inc. (AWS), an Amazon.com, Inc. company, announced the general availability of Amazon Q, the most capable generative artificial intelligence (AI)-powered assistant for accelerating software development and leveraging companies' internal data.

Amazon Q not only generates highly accurate code, it also tests, debugs, and has multi-step planning and reasoning capabilities that can transform (e.g., perform java version upgrades) and implement new code generated from developer requests. Amazon Q also makes it easier for employees to get answers to questions across business data such as company policies, product information, business results, code base, employees, and many other topics by connecting to enterprise data repositories to summarize the data logically, analyze trends, and engage in dialog about the data. Today, AWS is also introducing Amazon Q Apps, a new and powerful capability that lets employees build generative AI apps from their company's data. Employees simply describe the type of app they want, in natural language, and Q Apps will quickly generate an app that accomplishes their desired task, helping them streamline and automate their daily work with ease and efficiency.

"Amazon Q is the most capable generative AI-powered assistant available today with industry-leading accuracy, advanced agents capabilities, and best-in-class security that helps developers become more productive and helps business users to accelerate decision making," said Dr. Swami Sivasubramanian, vice president of Artificial Intelligence and Data at AWS. "Since we announced the service at re:Invent, we have been amazed at the productivity gains developers and business users have seen. Early indications signal Amazon Q could help our customers' employees become more than 80% more productive at their jobs; and with the new features we're planning on introducing in the future, we think this will only continue to grow."

Amazon Q Developer

Today, developers tell us that only 30% (or less) of their time is spent on coding, while the rest is spent performing tedious and repetitive tasks. This could be researching best practices from various parts of the web or learning how things work through documentation, forums, and conversations with colleagues. Developers also have to manage infrastructure and resources, troubleshoot and resolve errors, and understand operating costs. When they switch projects, they have to spend time learning the existing code base to understand its programming logic. Finally, there is all the work of testing and refactoring code, upgrading applications, debugging and optimization, and ensuring security by having to carry out vulnerability scanning and applying appropriate security fixes in a timely fashion. Companies want to empower their developers to spend less time on this coding muck and more time on creating unique experiences for their end users, while being able to deploy faster.

Q assists developers and IT professionals (IT pros) with all of their tasks—from coding, testing, and upgrading applications, to troubleshooting, performing security scanning and fixes, and optimizing AWS resources. Amazon Q delivers advanced and tailored generative AI capabilities, including:

■ Most accurate coding recommendations: Amazon Q helps developers build faster and more securely by generating code suggestions and recommendations in near real time. Customers such as Blackberry, BT Group, and Toyota are already using Q to increase developer productivity and speed up innovation in their organizations. Amazon Q Developer has the highest reported code acceptance rates in the industry, for assistants that perform multi-line code suggestions, with BT Group recently sharing that they accepted 37% of Q's code suggestions and National Australia Bank reporting 50% acceptance rates. Q also has a powerful customization capability that securely leverages a customer's internal code base to provide more relevant and useful code recommendations. With this capability, Q is an expert on your code and provides recommendations that are more relevant to save even more time. Q keeps customizations completely private, and the underlying foundation model (FM) does not use them for training, protecting customers' valuable intellectual property.

■ Amazon Q Developer Agents: Q has a unique capability, called agents, which can autonomously perform a range of tasks–everything from implementing features, documenting, and refactoring code, to performing software upgrades. Developers can simply ask Amazon Q to implement an application feature (such as asking it to create an "add to favorites" feature in a social sharing app), and the agent will analyze their existing application code and generate a step-by-step implementation plan. Developers can collaborate with the agent to review and iterate on the plan before the agent implements it, connecting multiple steps together and applying updates across source files, code blocks, and test suites. Carrying out these tasks, Q has achieved the highest scores of any software development assistant available today, scoring 13.82% on the SWE-Bench Leaderboard and 20.33% on the SWE-Bench Leaderboard (Lite), a dataset that benchmarks coding capabilities.
To save customers months, even years, of time upgrading applications, Q can also automate and manage the entire upgrade process–with Java conversions available today and .Net conversions coming soon to help people move from Windows to Linux. In their integrated development environment (IDE), developers simply ask Amazon Q to "transform" their project and the agent analyzes application source code, generates new code in the target language or version, executes tests, and completes all code changes. A five-person team at Amazon used Q to upgrade more than 1,000 production applications from Java 8 to Java 17 in just two days (the average time per application was less than 10 minutes), saving months of time, and improving application performance–previously, many of these applications would each take a couple of days to upgrade.

■ Best-in-class security vulnerability scanning and remediation: Q scans code for hard-to-detect vulnerabilities, such as exposed credentials and log injection. With a single click, Q automatically suggests remediations tailored to the application code, allowing developers to quickly accept fixes with confidence. Q's security scanning capabilities outperform leading publicly benchmarkable tools on detection across most of the popular programming languages, helping to significantly improve the security and code quality of a developer's application.

■ Q is an expert on AWS and optimizing your AWS environment: Amazon Q Developer is an expert on AWS and is in the console to help IT pros optimize their cloud environments, as well as diagnose and resolve errors and networking issues, select instances, optimize structured query language (SQL) queries, extract, transform, and load (ETL) pipelines, and provide guidance on architectural best practices. To further help customers optimize their cloud environments, today Amazon Q Developer includes a new feature that helps customers list their AWS account resources, configurations, and analyze billing information and trends, making it easier for them to manage their accounts. For example, IT pros can simply ask, "What instances are currently running in us-east-1?" or "What's my S3 bucket encryption?" or "What were my EC2 costs by region last month?" and Amazon Q Developer will list the resources and details in a summarized answer with links to learn more.

Amazon Q's conversational interface is available wherever it is needed—in the AWS Console, in Slack, or in IDEs, including Visual Studio Code and JetBrains–to give developers the ability to use the conversational experience of Q within their favorite software development solutions. To extend the Q experience to more places developers work, AWS is announcing new partner extensions from Datadog and Wiz, and an integration with GitLab Duo that will offer joint customers a unified interface—whether working in AWS or GitLab. By integrating Amazon Q's generative AI capabilities with solutions that developers know, use, and trust, developers can update and create software faster.

Amazon Q Business

Organizations possess vast amounts of data spread across multiple documents, systems, and applications. Employees across every organization and department spend hours every week searching internal sources for information, piecing together analyses, writing reports, building presentations, gathering insights from dashboards, and adapting content for different audiences. Generative AI can help solve these challenges. However, the offerings available today are not connected to business data or internal resources and are not built from the ground up with security in mind. Because of these barriers, many organizations cannot safely tap into the full potential of generative AI.

Q Business is a generative AI–powered assistant that can answer questions, provide summaries, generate content, and securely complete tasks based on data and information in your enterprise systems. It empowers employees to be more creative, data-driven, efficient, prepared, and productive:

■ Q unites more data sources than any other generative AI assistant available today: Amazon Q Business easily and securely connects to 40+ commonly used business tools, such as wikis, intranets, Atlassian, Gmail, Microsoft Exchange, Salesforce, ServiceNow, Slack, and Amazon Simple Storage Service (Amazon S3)–more than any other generative AI assistant available today. Simply point Q at your enterprise data repositories, and it will search all of your data, summarize logically, analyze trends, and engage in dialog with end users about the data. This helps business users to access all of their data, no matter where it resides in their organization.

■ : Amazon Q Business seamlessly integrates with a customer's existing identities, roles, and access permissions to personalize the interactions for each individual user, while maintaining the highest levels of security. It generates accurate responses based on enterprise information, and customers can restrict sensitive topics, block keywords, and filter out inappropriate content. Q also does not use customer content to train the underlying models for anybody else. Amazon Q Business outperforms all published results for other assistants on correctness, truthfulness, and helpfulness for general Q&A (using the MultiHop-RAG dataset), as well as industries like finance (using a FiQA dataset sample) and technology (using a LoTTE dataset sample).

■ Inventive generative BI allows analysts to build detailed dashboards in minutes and business users to get insights fast: Amazon Q brings its advanced generative AI technology to Amazon QuickSight, AWS's unified Business Intelligence (BI) service built for the cloud. With Amazon Q in QuickSight, customers get a Generative BI assistant that allows business analysts to use natural language to build BI dashboards in minutes and easily create visualizations and complex calculations. It is also the only BI product where business users can get AI-driven executive summaries of dashboards, ask questions of data beyond what is presented in the dashboards, and create detailed and customizable data stories highlighting key insights, trends, and drivers. Business users can ask to "build a story about how the business has changed over the last month for a business review with leadership;" and in seconds, Amazon Q creates a narrative with specific insights and supporting visuals, including specific ideas of how to improve the business. Users can choose to layout the content produced by Q in an easy to share document or presentation where they can customize text, images, and themes, and use Amazon Q to rewrite and improve the text.

■ First-of-its-kind capability that helps every employee go from conversation to generative AI-powered app in seconds: Today, AWS is announcing the new Amazon Q Apps capability (in preview). Amazon Q Apps allows employees to easily and quickly create generative AI-powered apps based on their company data, without requiring any prior coding experience. With Q Apps, employees simply describe the app they want, in natural language, or they can take an existing conversation where Amazon Q Business helped them solve a problem, and with one click, Q will instantly generate an app that accomplishes their desired task that can be easily shared across their organization.

For example, creating employee onboarding plans for new recruits can be a long and laborious process. They require many hours of searching through different data stores and documents to find the appropriate content for the new employee; and often, the content is out of date or not specific enough to their role. With Q, an HR professional could simply describe they want an app that will create an onboarding plan for a new employee that utilizes the company's existing best practices, and has an input field for employee ID that personalizes the onboarding plan to their role by drawing from internal data sources specific to their job family. In a matter of seconds, Amazon Q Apps will build an app that can automatically generate a personalized onboarding plan tailored to the employee, their role, and the department using the latest best practices. The HR professional can then share the app with hiring managers across the company to instantly build personalized onboarding plans for their own teams. Now, with Amazon Q Apps, business users can easily, quickly, and securely build an app based on enterprise information to improve their work productivity.