![\"\"](\"https:\/\/ljdevice.com.tw\/wp-content\/uploads\/2023\/12\/2023-12-05_110504-294x200.jpg\")
<\/p>\nNovember 29, 2023<\/p>\n
<\/p>\n
Amazon is launching an AI-powered chatbot for AWS customers called Q.<\/p>\n
Unveiled during a keynote at\u00a0Amazon\u2019s AWS re:Invent conference in Las Vegas<\/a>\u00a0this morning, Q \u2014 starting at $20 per user per year, now in public preview \u2014 can answer questions like \u201cHow do I build a web application using AWS?\u201d Trained on 17 years\u2019 worth of AWS knowledge, Q will offer a list of potential solutions along with reasons you might consider its proposals.<\/p>\n \u201cYou can easily chat, generate content and take actions [with Q],\u201d AWS CEO Adam Selipsky said onstage. \u201cIt\u2019s all informed by an understanding of your systems, your data repositories and your operations.\u201d<\/p>\n AWS customers configure Q by connecting it to \u2014 and customizing it with \u2014 organization-specific apps and software like Salesforce, Jira, Zendesk, Gmail and Amazon S3 storage instances. Q indexes all connected data and content, \u201clearning\u201d aspects about a business, including its organizational structures, core concepts and product names.<\/p>\n From a web app, a company can ask Q to analyze, for example, which product features its customers are struggling with and possible ways to improve them \u2014 or, \u00e0 la\u00a0ChatGPT<\/a>, upload a file (a Word doc, PDF, spreadsheet and the like) and ask questions about that file. Q draws on its connections, integrations and data, including business-specific data, to come up with responses along with citations.<\/p>\n Q goes beyond simply answering questions. The assistant can generate or summarize content such as blog posts, press releases and emails. And it take actions on a user\u2019s behalf through a set of configurable plugins, like automatically creating service tickets, notifying particular teams in Slack and updating dashboards in ServiceNow.<\/p>\n To prevent mistakes, Q has users inspect actions that it\u2019s about to take before they run<\/p>\n and link to the results for validation.<\/p>\n Accessible from the AWS Management Console and the aforementioned web app, as well as existing chat apps like Slack, Q has a thorough understanding of AWS and the products and services available through it, as you might imagine. Amazon says that Q can understand the nuances of app workloads on AWS, suggesting AWS solutions for apps that only run for a few seconds versus minutes or hours or apps that only very infrequently access storage, for instance.<\/p>\n Onstage, Selipsky gave the example of an app that relies on high-performance video encoding and transcoding. Asked about the best EC2 instance for the app in question, Q would give a list taking into account performance and cost considerations, Selipsky said.<\/p>\n \u201cI really believe this is going to be transformative,\u201d he said, referring to Q. \u201cWe want lots of different kinds of people who do lots of different kinds of work to benefit from Amazon Q.\u201d<\/p>\n Image Credits:<\/strong>\u00a0Frederic Lardinois \/ TechCrunch<\/p>\n<\/div>\n Q can also troubleshoot things like network connectivity issues, analyzing network configurations to provide remediation steps.<\/p>\n And Q ties in with\u00a0CodeWhisperer<\/a>, Amazon\u2019s service that can generate and interpret app code. Within a supported IDE (e.g., Amazon\u2019s CodeCatalyst), Q can generate tests to benchmark software drawing on knowledge of a customer\u2019s code. Q can also create a draft plan and documentation for implementing new features in software or transforming code and upgrading code packages, repositories and frameworks \u2014 plans that can then be refined and executed using natural language.<\/p>\n Selipsky says that a small team within Amazon used Q internally to upgrade around 1,000 apps from Java 8 to Java 17 \u2014 and test those apps \u2014 in just two days.<\/p>\n Q\u2019s code transformation features only support upgrading Java 8 and Java 11 apps to Java 17 (with .NET Framework-to-cross-platform .NET coming soon), while all of Q\u2019s code-related features \u2014 including code transformation \u2014 require a CodeWhisperer Professional\u00a0subscription<\/a>. No word on when or whether the subscription requirement will change.<\/p>\n Amazon says that it\u2019s also building Q its first-party products like AWS Supply Chain and QuickSight, a business analytics service. Q within QuickSight can provide visualization options for business reports, automatically reformatting them, or answer questions about the data referenced or contained in a report. In AWS Supply Chain, Q can respond to queries like \u201cWhat\u2019s causing the delay in my shipments?\u201d with up-to-minute analyses.<\/p>\n Q is also making its way into Amazon\u2019s contact center software, Amazon Connect. Now \u2014 powered by Q \u2014 customer service agents can get proposed responses to customer questions with suggested actions and links to related support articles without having to type those customer questions in a text bar. Q also generates a post-call summary supervisors can use to track follow-up steps.<\/p>\n Selipsky underlined several times throughout the keynote that the answers Q gives \u2014 and the actions it takes \u2014 are fully controllable and filterable. Q will only return info a user\u2019s authorized to see, and admins can restrict sensitive topics, having Q filter out inappropriate questions and answers where necessary.<\/p>\n To mitigate\u00a0hallucinations<\/a>\u00a0(i.e. instances where Q might invent facts, a common problem with generative AI systems), admins can choose to have Q only pull from company documents as opposed to knowledge from any underlying models. The models driving Q \u2014 a mix of models from Bedrock, Amazon\u2019s AI dev platform, including Amazon\u2019s own in-house\u00a0Titan<\/a>\u00a0family \u2014 don\u2019t train on a customer\u2019s data, Selipsky said.<\/p>\n Those bullet points were no doubt aimed at companies wary of adopting generative AI for liability and security reasons.\u00a0Over a dozen companies<\/a>\u00a0have issued bans or restrictions on ChatGPT, expressing concerns about how data entered into the chatbot might be used and the risk of data leaks.<\/p>\n \u201cIf your user doesn\u2019t have permission to access something without Q, they can\u2019t access it\u00a0with<\/em>\u00a0Q either,\u201d Selipsky said. \u201cQ understands and respects your existing identities, your roles and your permissions \u2026 we\u2019re never going to use [business content] to train the underlying models.\u201d<\/p>\n Heavy privacy emphasis aside, in many ways, Q seems like Amazon\u2019s answer to Microsoft\u2019s\u00a0Copilot for Azure<\/a>\u00a0\u2014 which is was in turn Microsoft\u2019s answer to\u00a0Duet AI<\/a>\u00a0in Google Cloud. Both Copilot for Azure and Duet AI take the form of chat-driven assistants for cloud customers, suggesting configurations for apps and environments and helping with troubleshooting by identifying potential issues \u2014 and solutions.<\/p>\n Image Credits:<\/strong>\u00a0Frederic Lardinois \/ TechCrunch<\/p>\n<\/div>\n But Q appears to be a bit more comprehensive, touching on a wide range of business intelligence, programming and configuration use cases. Ray Wang, founder and principal analyst at Constellation Research, told TechCrunch that he believes it\u2019s the \u201cmost important\u201d announcement at re:Invent so far.<\/p>\n \u201cIt\u2019s about arming developers with AI so that they\u2019re successful,\u201d he said \u2014 an important note to raise considering that\u00a0according<\/a>\u00a0to at least one recent survey, many companies piloting generative AI are struggling to find business use cases and overcome badly conceived implementations.<\/p>\n We\u2019ll just have to see if Q works as well as Amazon says it does.<\/p>\n<\/div>\n\n<\/div>\n![\"Amazon](\"https:\/\/techcrunch.com\/wp-content\/uploads\/2023\/11\/IMG_3851.jpg\")
<\/p>\n<\/div>\n<\/div>\n<\/div>\n![\"Amazon](\"https:\/\/techcrunch.com\/wp-content\/uploads\/2023\/11\/IMG_3852.jpg\")
<\/p>\n