Discover How The Q Chatbot Can Boost Your AWS Productivity With AI

Amazon has announced a new AI-powered assistant for its cloud computing platform, AWS. The assistant, called Q chatbot, can help AWS customers with various tasks, such as building web applications, generating content, and troubleshooting issues.

Q chatbot was unveiled during a keynote at Amazon’s re:Invent conference in Las Vegas on Wednesday. The chatbot, which is now in public preview, starts at $20 per user per year. Q chatbot is trained on 17 years’ worth of AWS knowledge and can offer a list of potential solutions along with reasons for its proposals.

How the Q chatbot works

AWS customers can configure Q chatbot by connecting it to their organization-specific apps and software, such as Salesforce, Jira, Zendesk, Gmail, and Amazon S3 storage instances. The chatbot indexes all the connected data and content and learns about the business, including its organizational structures, core concepts, and product names.

Customers can access the chatbot from the AWS Management Console, a web app, or existing chat apps like Slack. They can ask the chatbot questions like “How do I build a web application using AWS?” or upload a file (such as a Word doc, PDF, or spreadsheet) and ask questions about that file. Q chatbot draws on its connections, integrations, and data, including business-specific data, to come up with responses along with citations.

What the chatbot can do

Q chatbot can do more than just answer questions. The assistant can also generate or summarize content, such as blog posts, press releases, and emails. Moreover, it can take actions on behalf of the user through a set of configurable plugins, such as automatically creating service tickets, notifying particular teams in Slack, and updating dashboards in ServiceNow.

To prevent mistakes, the Q chatbot allows users to inspect actions that it is about to take before they run and link to the results for validation.

The chatbot has a thorough understanding of AWS and the products and services available through it. It can understand the nuances of app workloads on AWS and suggest AWS solutions for different scenarios. For example, the chatbot can recommend the best EC2 instance for an app that relies on high-performance video encoding and transcoding, taking into account performance and cost considerations.

The chatbot can also troubleshoot issues, such as network connectivity problems, by analyzing network configurations and providing remediation steps.

How Q chatbot integrates with other AWS services

Q chatbot integrates with CodeWhisperer, Amazon’s service that can generate and interpret app code. Within a supported IDE (such as Amazon’s CodeCatalyst), the chatbot can generate tests to benchmark software, drawing on knowledge of the customer’s code. The chatbot can also create a draft plan and documentation for implementing new features in software or transforming code and upgrading code packages, repositories, and frameworks. These plans can then be refined and executed using natural language.

The chatbot’s code transformation features currently only support upgrading Java 8 and Java 11 apps to Java 17, with .NET Framework-to-cross-platform .NET coming soon. All of the chatbot’s code-related features, including code transformation, require a CodeWhisperer Professional subscription.

Q chatbot is also being built into Amazon’s first-party products, such as AWS Supply Chain and QuickSight. In QuickSight, the chatbot can provide visualization options for business reports, automatically reformatting them, or answering questions about the data in the report. In AWS Supply Chain, the chatbot can respond to queries like “What’s causing the delay in my shipments?” with up-to-date analyses.

The chatbot is also making its way into Amazon’s contact center software, Amazon Connect. With the chatbot, customer service agents can get proposed responses to customer questions with suggested actions and links to related support articles without having to type the questions in a text bar. The chatbot also generates a post-call summary that supervisors can use to track follow-up steps.

How Q chatbot ensures security and privacy

Q chatbot is designed to ensure security and privacy for its users. The chatbot will only return information that the user is authorized to see, and admins can restrict sensitive topics, having the chatbot filter out inappropriate questions and answers where necessary.

To mitigate hallucinations, which are instances where the chatbot might invent facts, a common problem with generative AI systems, admins can choose to have the chatbot only pull from company documents instead of knowledge from any underlying models. The models driving the chatbot, which are a mix of models from Bedrock, Amazon’s AI development platform, including Amazon’s own in-house Titan family, do not train on the customer’s data.

Q chatbot also respects the user’s existing identities, roles, and permissions. “If your user doesn’t have permission to access something without Q, they can’t access it with Q either,” AWS CEO Adam Selipsky said onstage.

Why Q chatbot is important

Q chatbot is Amazon’s answer to Microsoft’s Copilot for Azure and Google’s Duet AI, which are chat-driven assistants for cloud customers. However, the chatbot seems to be more comprehensive, touching on a wide range of business intelligence, programming, and configuration use cases.

Selipsky said that he believes the chatbot is going to be transformative. “We want lots of different kinds of people who do lots of different kinds of work to benefit from Amazon Q,” he said.

Ray Wang, founder and principal analyst at Constellation Research, told that he believes Q chatbot is the most important announcement at re:Invent so far. “It’s about arming developers with AI so that they’re successful,” he said.

Q chatbot is an ambitious project that aims to help AWS customers with various tasks using AI. We’ll have to see if the chatbot works as well as Amazon says it does.