{"id":431,"date":"2025-10-16T13:16:22","date_gmt":"2025-10-16T18:16:22","guid":{"rendered":"https:\/\/www.mrc-productivity.com\/newsletter\/?p=431"},"modified":"2025-10-27T09:26:48","modified_gmt":"2025-10-27T14:26:48","slug":"fall-2025-m-power-update-ai-comes-to-m-power","status":"publish","type":"post","link":"https:\/\/www.mrc-productivity.com\/newsletter\/2025\/10\/fall-2025-m-power-update-ai-comes-to-m-power\/","title":{"rendered":"Fall 2025 m-Power Update: AI comes to m-Power!"},"content":{"rendered":"<p>Development efforts for the m-Power platform continue to be guided by two factors: customer requests and industry trends. Our upcoming release addresses both by focusing on AI.<\/p>\n<p>Many of our clients have asked how artificial intelligence fits into m-Power. This newsletter introduces the core AI concepts, explains how they\u2019re available within m-Power, and shows how you can apply them in your own applications for end users.<\/p>\n<h2>Two Videos to Help You Learn More<\/h2>\n<ol>\n<li><strong>Webinar Replay<\/strong>: We covered the enhancements coming in m-Power&#8217;s AI Release Candidate on October 23rd. You can watch the webinar replay below:\n<div class=\"ast-oembed-container\" style=\"height: 100%;\"><iframe loading=\"lazy\" title=\"Webinar Replay: Overview of m-Power&#039;s AI Enhancements\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/i3UeQo5e2jo?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/div>\n<\/li>\n<li><strong>m-Power AI Project:<\/strong> In this demo video, we show you how to add AI assistants and AI features into an existing application and workflow. You&#8217;ll learn how to create AI tools that interact with your business data and fit into existing processes.\n<div class=\"ast-oembed-container\" style=\"height: 100%;\"><iframe loading=\"lazy\" title=\"How to Bring AI to your Business Data with m-Power\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/CHAe3X5sHPE?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/div>\n<\/li>\n<\/ol>\n<h2 data-start=\"0\" data-end=\"13\"><\/h2>\n<h2 data-start=\"0\" data-end=\"13\">What is AI?<\/h2>\n<p data-start=\"15\" data-end=\"321\">Artificial Intelligence (AI) has moved into everyday use, with tools like ChatGPT making conversational interactions common. While chat is a familiar entry point, <strong data-start=\"175\" data-end=\"206\">AI goes far beyond chatbots<\/strong>. It can <strong data-start=\"215\" data-end=\"247\">categorize and classify data<\/strong>, generate summaries, and <strong data-start=\"273\" data-end=\"295\">automate workflows<\/strong> across your applications.<\/p>\n<p data-start=\"323\" data-end=\"585\" data-is-last-node=\"\" data-is-only-node=\"\">At the end of this document, we&#8217;ve included\u00a0two live demos on CrazyBikes.com to see how this works in real time.<\/p>\n<h2 data-start=\"0\" data-end=\"19\">AI Terms to Know<\/h2>\n<p data-start=\"0\" data-end=\"247\"><strong data-start=\"21\" data-end=\"36\">AI Provider<\/strong> \u2013 The service that processes your AI requests (e.g., OpenAI, Microsoft, Anthropic, IBM, Groq). We support multiple providers so you can choose the option that best aligns with your data, security, and compliance needs.<\/p>\n<p data-start=\"249\" data-end=\"495\"><strong data-start=\"249\" data-end=\"279\">LLM (Large Language Model)<\/strong> \u2013 Providers offer different models for different tasks (some excel at short answers, others at creative output or images). Pricing varies by model, so understanding usage cost is an important part of your selection.<\/p>\n<p data-start=\"497\" data-end=\"787\"><strong data-start=\"497\" data-end=\"509\">API Keys<\/strong> \u2013 Credentials used to authenticate with your chosen provider and associate usage with your account.<br data-start=\"584\" data-end=\"587\" \/><strong data-start=\"587\" data-end=\"596\">Note:<\/strong> When making AI requests <strong data-start=\"621\" data-end=\"653\">inside the m-Power interface<\/strong>, you\u2019ll use an mrc-provided key at no charge. To add AI to <strong data-start=\"713\" data-end=\"739\">generated applications<\/strong>, select a provider and obtain your own API key.<\/p>\n<p data-start=\"789\" data-end=\"1006\"><strong data-start=\"789\" data-end=\"799\">Tokens<\/strong> \u2013 Providers count tokens for both input and output (roughly word-like units). Your total tokens determine usage cost. Rates depend on the model, but typical rates make large volumes relatively inexpensive.<\/p>\n<p data-start=\"1008\" data-end=\"1212\"><strong data-start=\"1080\" data-end=\"1115\">AI Assistant (m-Power template)<\/strong> \u2013 A new template that connects to your selected provider. Use it as a chatbot, or call it from <strong data-start=\"1211\" data-end=\"1231\">m-Power Workflow<\/strong> to pass data automatically via forms or scheduled jobs.<\/p>\n<p data-start=\"1214\" data-end=\"1297\"><strong data-start=\"1214\" data-end=\"1230\">User Message<\/strong> \u2013 The end user\u2019s instruction or question entered into the chatbot.<\/p>\n<p data-start=\"1299\" data-end=\"1467\" data-is-last-node=\"\" data-is-only-node=\"\"><strong data-start=\"1299\" data-end=\"1316\">System Prompt<\/strong> \u2013 The developer-written guidance that tells the assistant how to behave, what rules to follow, and how to answer. These are authored in <strong data-start=\"1453\" data-end=\"1466\">m-Painter<\/strong>.<\/p>\n<p data-start=\"1548\" data-end=\"1789\"><strong data-start=\"1548\" data-end=\"1569\">Content Retriever (m-Power template)<\/strong> \u2013 By default, AI starts with general knowledge. But what if you need it to understand a specific topic at your organization? For example, maybe you want to load thousands of old hotline tickets or your HR onboarding process. With an m-Power <strong data-start=\"223\" data-end=\"244\">Content Retriever<\/strong>, you can upload these documents to your system. Then, when an <strong data-start=\"307\" data-end=\"323\">AI Assistant<\/strong> is trained with that retriever, it can answer targeted questions about those materials. This works best for content that\u2019s relatively static.<\/p>\n<p data-start=\"1791\" data-end=\"1982\" data-is-last-node=\"\" data-is-only-node=\"\"><strong data-start=\"1791\" data-end=\"1809\">Tool Functions<\/strong> \u2013 Unlike a content retriever, tool functions are best for information that changes constantly. For example, you can use a tool function to check the current quantity on hand for a given item. Tool functions call m-Power retrievals in real time, so your AI Assistant can access up-to-date information.<\/p>\n<article class=\"text-token-text-primary w-full focus:outline-none [--shadow-height:45px] has-data-writing-block:pointer-events-none has-data-writing-block:-mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&amp;:has([data-writing-block])&gt;*]:pointer-events-auto [content-visibility:auto] supports-[content-visibility:auto]:[contain-intrinsic-size:auto_100lvh] scroll-mt-[calc(var(--header-height)+min(200px,max(70px,20svh)))]\" dir=\"auto\" tabindex=\"-1\" data-turn-id=\"request-WEB:dc52678f-d8b1-46f3-b6bd-646f74f44b88-22\" data-testid=\"conversation-turn-20\" data-scroll-anchor=\"true\" data-turn=\"assistant\">\n<div class=\"text-base my-auto mx-auto pb-10 [--thread-content-margin:--spacing(4)] thread-sm:[--thread-content-margin:--spacing(6)] thread-lg:[--thread-content-margin:--spacing(16)] px-(--thread-content-margin)\">\n<div class=\"[--thread-content-max-width:40rem] thread-lg:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-width) flex-1 group\/turn-messages focus-visible:outline-hidden relative flex w-full min-w-0 flex-col agent-turn\" tabindex=\"-1\">\n<div class=\"flex max-w-full flex-col grow\">\n<div class=\"min-h-8 text-message relative flex w-full flex-col items-end gap-2 text-start break-words whitespace-normal [.text-message+&amp;]:mt-1\" dir=\"auto\" data-message-author-role=\"assistant\" data-message-id=\"d7bf88a8-b884-4fed-9023-791b4fa65fa6\" data-message-model-slug=\"gpt-5-thinking\">\n<div class=\"flex w-full flex-col gap-1 empty:hidden first:pt-[1px]\">\n<div class=\"markdown prose dark:prose-invert w-full break-words light markdown-new-styling\">\n<h2 data-start=\"0\" data-end=\"44\">How AI is being added directly to m-Power<\/h2>\n<p data-start=\"46\" data-end=\"299\">The m-Power interface has been updated to give developers several built-in ways to use AI. These features are included for customers on maintenance and warranty support at no additional charge. You can find the interface API key in your customer portal.<\/p>\n<p data-start=\"303\" data-end=\"545\"><strong data-start=\"303\" data-end=\"325\">AI Support Chatbot<\/strong> \u2013 If you\u2019re unsure how to do something in m-Power, use the chatbot for guidance. It\u2019s trained on our documentation and training materials. You can still contact support anytime\u2014this is simply a quick, self-serve option.<\/p>\n<p data-start=\"549\" data-end=\"726\"><strong data-start=\"549\" data-end=\"576\">AI System Prompt Helper<\/strong> \u2013 When creating prompts, paste your draft into the helper and get suggestions to refine it. Available in <strong data-start=\"682\" data-end=\"695\">m-Painter<\/strong> for the AI Assistant template.<\/p>\n<p data-start=\"730\" data-end=\"874\"><strong data-start=\"730\" data-end=\"755\">m-Painter HTML Helper<\/strong> \u2013 From within <strong data-start=\"770\" data-end=\"783\">m-Painter<\/strong>, describe the change you want and the AI will apply it in the WYSIWYG view or source HTML.<\/p>\n<p data-start=\"878\" data-end=\"982\" data-is-last-node=\"\"><strong data-start=\"878\" data-end=\"898\">AI Chart Builder<\/strong> \u2013 <span style=\"font-weight: 400;\">Not sure how to configure your graph? No problem! Describe the chart you need, and the builder generates the configuration for you.<\/span><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"z-0 flex min-h-[46px] justify-start\">\n<h2 data-start=\"0\" data-end=\"44\">How you can add AI to your generated apps<\/h2>\n<p data-start=\"46\" data-end=\"234\">The options are limitless. Start by selecting an <strong data-start=\"94\" data-end=\"109\">AI provider<\/strong>, setting up billing with that provider, and obtaining an <strong data-start=\"167\" data-end=\"178\">API key<\/strong>. After you configure the key in m-Power, you can begin.<\/p>\n<p data-start=\"236\" data-end=\"494\"><strong data-start=\"236\" data-end=\"261\">Common first projects<\/strong> include a customer support chatbot or an internal reference assistant for employees.<br data-start=\"346\" data-end=\"349\" \/><strong data-start=\"349\" data-end=\"375\">More advanced projects<\/strong> might train AI on historical orders to assist with forecasting, or automate recurring tasks (e.g., billing workflows).<\/p>\n<h2 data-start=\"236\" data-end=\"494\">Next Steps<\/h2>\n<p data-start=\"236\" data-end=\"494\">We recognize that some teams are exploring AI, while others are being asked to implement it quickly. To help, we\u2019re offering a <strong style=\"font-size: 16px;\" data-start=\"643\" data-end=\"679\">one-time, complimentary half-day<\/strong><span style=\"font-size: 16px;\"> of AI consulting for customers. We can assist with provider selection, configuration, and the design of key components (prompts, content retrievers, tool functions, and workflows). If additional time is needed, we can discuss options.<\/span><\/p>\n<h2 data-start=\"0\" data-end=\"23\">Examples you can try<\/h2>\n<ul data-start=\"25\" data-end=\"213\" data-is-last-node=\"\" data-is-only-node=\"\">\n<li data-start=\"69\" data-end=\"138\">\n<p data-start=\"71\" data-end=\"138\"><strong data-start=\"71\" data-end=\"94\">CrazyBikes Chatbot:<\/strong> <a class=\"decorated-link\" href=\"https:\/\/crazybikes.com\/CRAZYBIKES.I00010s\" target=\"_new\" rel=\"noopener\" data-start=\"95\" data-end=\"136\" data-is-only-node=\"\">https:\/\/crazybikes.com\/CRAZYBIKES.I00010s<\/a><\/p>\n<\/li>\n<li data-start=\"139\" data-end=\"213\" data-is-last-node=\"\">\n<p data-start=\"141\" data-end=\"213\" data-is-last-node=\"\"><strong data-start=\"141\" data-end=\"169\">CrazyBikes Order Helper:<\/strong> <a class=\"decorated-link\" href=\"https:\/\/crazybikes.com\/mrc\/CBPORTAL.I00020s\" target=\"_new\" rel=\"noopener\" data-start=\"170\" data-end=\"213\" data-is-last-node=\"\" data-is-only-node=\"\">https:\/\/crazybikes.com\/mrc\/CBPORTAL.I00020s<\/a><\/p>\n<\/li>\n<\/ul>\n<\/div>\n<\/div>\n<\/div>\n<\/article>\n","protected":false},"excerpt":{"rendered":"<p>Development efforts for the m-Power platform continue to be guided by two factors: customer requests and industry trends. Our upcoming release addresses both by focusing on AI. Many of our clients have asked how artificial intelligence fits into m-Power. This newsletter introduces the core AI concepts, explains how they\u2019re available within m-Power, and shows how &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"https:\/\/www.mrc-productivity.com\/newsletter\/2025\/10\/fall-2025-m-power-update-ai-comes-to-m-power\/\"> <span class=\"screen-reader-text\">Fall 2025 m-Power Update: AI comes to m-Power!<\/span> Read More &raquo;<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":true,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","footnotes":""},"categories":[3],"tags":[],"class_list":["post-431","post","type-post","status-publish","format-standard","hentry","category-customer-newsletter"],"_links":{"self":[{"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/posts\/431","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/comments?post=431"}],"version-history":[{"count":16,"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/posts\/431\/revisions"}],"predecessor-version":[{"id":448,"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/posts\/431\/revisions\/448"}],"wp:attachment":[{"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/media?parent=431"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/categories?post=431"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.mrc-productivity.com\/newsletter\/wp-json\/wp\/v2\/tags?post=431"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}