What is Amazon Q?

What you need to know about the new generative AI assistant from AWS.

Background

Since the release of ChatGPT the 2 main objections to using large language models (LLMs) for business were:

• Hallucinations — when the LLM generates inaccurate but realistic sentences.
• Security — OpenAI’s ChatGPT, the first mover on releasing LLMs, could take all the information typed into the chat bot and use it for future training.

Both of these are solved problems. Companies can host their own LLMs and use retrieval augmented generation (RAG) to ensure the models cite their sources.

But who is going to make this solution the best, easiest to maintain, and the cheapest for enterprise use?

The new Amazon Q

Amazon released Amazon Q, a generative AI-powered assistant designed to streamline work processes and enhance productivity in various business contexts.

What is it?

Amazon Q assists with answering questions, problem-solving, content generation, and taking actions based on company data, code, and systems. It can help with everyday tasks like summarizing documents, drafting emails, conducting research, and performing comparative analyses.

Business Expert. Out of the box it has 40+ built in connectors to index data from the most popular business apps such as: OneDrive, Google Drive, Teams, Gmail, PostgreSQL DB’s, and many more. All of your business information searchable through the LLM interface so Amazon Q can be an expert in your business.

Security First. Amazon is very much advertising the security and privacy. Your data is your data, never used to train any other LLM. It also respects the access control of the source data systems. So you cannot ask it about someone else’s emails, documents, or data, that you do not already have access to.

Key Features

• AWS Expert. Of course, Amazon Q is an expert in all the AWS API’s and familiar with the AWS Well-Architected Framework, documentation, and best practices.
• Business intelligence and data storytelling. Amazon Q integrates with Amazon QuickSight for Generative BI capabilities to facilitate the quick creation of compelling visuals and data stories, answer data-related queries, and summarize insights using natural language. This integration streamlines the process of interacting with data and extracting meaningful insights.
• Supply chain. The upcoming integration of Amazon Q in the AWS Supply Chain application illustrates its potential in logistics and supply management. It will enable users like inventory managers and supply planners to get intelligent answers about supply chain dynamics, explore ‘what-if’ scenarios, and make informed decisions about various supply chain choices.
• Software development. Amazon CodeWhisperer can work with Q in the AWS console and popular IDEs to provides expert guidance in coding through a conversational interface, enabling code explanation, code transformation for upgrades, and personalized coding suggestions including unit tests, debugging, and optimization. Before, AI would help people write some small blocks of code, now CodeWhisperer & Q can help edit your entire application, then pass the changes to a human for review.
• Contact center assistance. Within Amazon Connect, Amazon’s contact center service, Amazon Q uses real-time conversations and relevant company content to recommend appropriate responses or actions to customer service agents. This capability allows agents to provide more effective customer service by offering timely and accurate assistance based on the specific context of each customer interaction.

How much does it cost?

From Amazon Q FAQs.

• $20 per user/month business plan — covers general business and Amazon QuickSight expertise.
• $25 per user/month builder plan includes all Business plan features plus AWS-specific support for developers and IT professionals.
• Additional plans are available for specialized applications like QuickSight, Amazon Connect, and Amazon Supply Chain.