<\/p>\n\n\n\n
Adobe Target teams are sitting on an incredible amount of signal – activities, offers, audiences, A4T data, and years of experimentation history. The hard part isn\u2019t having data; it\u2019s knowing what to do next.<\/p>\n\n\n\n
In a new early-peek demo, we walked through the Adobe Intelligence Services<\/strong> we\u2019re building inside MiaProva to make that \u201cwhat next?\u201d question dramatically easier to answer. These services connect Adobe Target + Adobe Analytics + Gemini<\/strong> into a conversational experience that feels like chatting with an expert who already knows your program.<\/p>\n\n\n\n This post recaps what we showed in the video and how we see teams using it.<\/p>\n\n\n\n Once an organization enables our Gemini integration<\/strong>, it doesn\u2019t just power one feature\u2014it unlocks AI across the MiaProva platform:<\/p>\n\n\n\n Crucially, organizations can control their agents<\/strong>:<\/p>\n\n\n\n Instead of a one-size-fits-all assistant, each tenant gets an agent that\u2019s tuned to their business and experimentation culture.<\/p>\n\n\n\n At the heart of the demo is a Model Context Protocol (MCP)\u2013style<\/strong> experience for Adobe Target. Think of it as:<\/p>\n\n\n\n \u201cWhat if a knowledgeable practitioner could sit on top of your Target APIs and your analytics, 24\/7, and answer questions on demand?\u201d<\/p>\n<\/blockquote>\n\n\n\n You start a new conversation, and the agent resets context for a clean session. A simple opener like:<\/p>\n\n\n\n \u201cWhat things can you do?\u201d<\/em><\/p>\n<\/blockquote>\n\n\n\n returns a guided overview of capabilities so users can explore without needing to memorize commands or API docs.<\/p>\n\n\n\n Behind the scenes, the agent is wired into Adobe Target APIs<\/strong> and, where available, Adobe Analytics \/ A4T<\/strong> so it can do much more than just describe concepts. It can act<\/strong> and analyze<\/strong>, not just chat.<\/p>\n\n\n\n In the demo, we asked:<\/p>\n\n\n\n \u201cWith the holiday season fast approaching, how do you recommend our organization makes use of Adobe Target?\u201d<\/em><\/p>\n<\/blockquote>\n\n\n\n Instead of spitting out generic \u201cbest practices,\u201d the agent:<\/p>\n\n\n\n It\u2019s the difference between reading a blog post about holiday optimization and having a system that looks at your actual account<\/strong> and says, \u201cHere\u2019s what you\u2019re currently doing\u2014and here\u2019s where you\u2019re leaving money on the table.\u201d<\/p>\n\n\n\n The agent isn\u2019t limited to strategy. It can also help with everyday operational questions, like:<\/p>\n\n\n\n \u201cList all approved or live activities.\u201d<\/em><\/p>\n<\/blockquote>\n\n\n\n The tool:<\/p>\n\n\n\n This is more than a thin layer over the APIs. We\u2019ve augmented the experience with additional context so teams can quickly move from:<\/p>\n\n\n\n All without leaving the conversation.<\/p>\n\n\n\n When you ask:<\/p>\n\n\n\n \u201cHow is the performance of this activity?\u201d<\/em><\/p>\n<\/blockquote>\n\n\n\n the agent taps into Adobe Analytics \/ A4T (Analytics for Target)<\/strong> where configured. In the demo, we show it:<\/p>\n\n\n\n We\u2019re actively expanding this integration so account-level reporting and activity-level deep dives are not just available in dashboards, but conversationally available<\/strong> in MiaProva.<\/p>\n\n\n\n That means you don\u2019t have to go hunting through multiple interfaces; you can ask, \u201cWhat happened?\u201d and get an answer that\u2019s grounded in the right data.<\/p>\n\n\n\n One of the most powerful flows in the demo is a full-account audit:<\/p>\n\n\n\n \u201cPlease examine my Adobe Target account and provide recommendations on ways I can use it more effectively, and provide a high-level audit of our company\u2019s use of it.\u201d<\/em><\/p>\n<\/blockquote>\n\n\n\n The agent then:<\/p>\n\n\n\n In the demo, it correctly calls out a strong emphasis on monitoring activities\u2014because that\u2019s true of the underlying account. This is the kind of insight that traditionally takes a seasoned practitioner several hours in the UI and documentation; now it can be generated in a few seconds and used as a starting point for planning.<\/p>\n\n\n\n We know many teams are constantly onboarding new practitioners. So we also showed how the agent can act as a training assistant<\/strong>:<\/p>\n\n\n\n \u201cHelp me set up my first A\/B activity in Adobe Target.\u201d<\/em><\/p>\n<\/blockquote>\n\n\n\n The agent responds with:<\/p>\n\n\n\n This turns MiaProva into more than a reporting and management layer. It becomes a coach<\/strong> that helps new team members ramp up faster while still aligning with your program\u2019s standards and definitions.<\/p>\n\n\n\n Profile scripts in Adobe Target are incredibly powerful\u2014but they can feel intimidating, particularly for those without a technical background.<\/p>\n\n\n\n In the video, we ask the agent to help with profile scripts. While Adobe Target doesn\u2019t offer an API to create them directly, the agent can still help by:<\/p>\n\n\n\n So instead of staring at a blank profile script editor, teams can start from a working, explanation-rich template and adapt from there.<\/p>\n\n\n\n What you see in the demo is just the beginning of our Adobe Intelligence Services roadmap. In active development right now:<\/p>\n\n\n\n
\n\n\n\nTurning on AI Across MiaProva<\/h2>\n\n\n\n
\n
\n
\n\n\n\nA MCP-Style Experience for Adobe Target<\/h2>\n\n\n\n
\n
\n
\n\n\n\nFrom \u201cHoliday Strategy\u201d to Concrete Target Plays<\/h2>\n\n\n\n
\n
\n
\n
\n\n\n\nQuery Your Adobe Target Account Like a Colleague<\/h2>\n\n\n\n
\n
\n
\n
\n\n\n\nDeep Dives Powered by Adobe Analytics & A4T<\/h2>\n\n\n\n
\n
\n
\n\n\n\nAutomated Account Audits & Strategic Recommendations<\/h2>\n\n\n\n
\n
\n
\n
\n
\n\n\n\nBuilt-In Training: \u201cHelp Me Set Up My First A\/B Test\u201d<\/h2>\n\n\n\n
\n
\n
\n\n\n\nDemystifying Profile Scripts for Non-Developers<\/h2>\n\n\n\n
\n
\n\n\n\nWhat\u2019s Coming Next<\/h2>\n\n\n\n