Debuting at Shoptalk (Booth #3255), this new AI agent explains product discovery results, suggests next steps, and automates actions — helping retailers create better shopping experiences
SAN FRANCISCO and LAS VEGAS, March 24, 2026 /PRNewswire/ -- SHOPTALK -- Constructor, the leading AI-powered search and product discovery platform for ecommerce companies, today unveiled Merchant Intelligence Agent (MIA), a new AI agent that brings conversational intelligence to ecommerce merchandising teams — helping them better understand and improve how shoppers discover products online. With MIA, merchandisers get their own personal assistant to do their most time-consuming work.
Teams can ask MIA natural-language questions about how and why products are surfaced in search and discovery across their ecommerce sites and other owned channels, use the agent to investigate campaign performance, ask it for recommendations to accomplish merchandising goals, and much more.
When data doesn't tell the whole story
When product discovery doesn't perform as expected — for example, a product that is expected to appear in search results suddenly doesn't, or a promoted item stops showing up prominently — ecommerce merchandisers (the specialists responsible for curating and strategically managing search and discovery results, campaigns, and product visibility across online storefronts) are often forced to "play detective."
Today's dashboards and analytics typically show what's happening, but understanding why often requires investigation. For instance, was a product marked out-of-stock in an upstream system? Was it blocked from showing for a particular query due to a rule accidentally set by a coworker?
As merchandising tools and systems grow increasingly complex, teams often have to piece together signals from ranking models, shopper behavior, and configuration rules to determine the cause — and how to fix it. The burden of reasoning falls on humans, with success hinging on time, experience, and a bit of luck and guesswork.
Introducing Merchant Intelligence Agent
MIA takes on the detective work itself. It proactively provides AI-generated explainers within Constructor's platform, so that merchandisers can understand the factors behind specific rankings, scores or results — without even needing to ask.
In addition, directly within the platform and through an AI-based chat interface, merchandisers can use plain language to pose questions to MIA, such as:
MIA gives clear explanations and recommendations grounded in each retailer's ecommerce store data, ranking logic and merchandising rules — helping teams move quickly from questions to action.
A key layer of Constructor's reasoning engine
MIA is the explainability layer of Constructor's Commerce Reasoning Engine, which processes real-time shopper behavior and context — along with historical interactions, survey responses, offline signals, merchandising configurations and more — to determine what to show each shopper and when. The agent brings greater transparency to product discovery decisions.
MIA is also the latest addition to Constructor's agentic product suite, which includes award-winning, consumer-facing AI agents: AI Shopping Agent (ASA) and AI Product Insights Agent (PIA). These agents enable shoppers to ask natural-language questions and receive personalized recommendations and information. With MIA, Constructor now delivers that same powerful and conversational intelligence to merchandising teams, bringing AI-driven reasoning directly into their workflows and saving them hours of time.
Features and capabilities
MIA operates across three core functions: explaining product discovery data and results, suggesting next steps, and even automating them. Key features include:
By interpreting complex data and translating it into clear next steps, MIA empowers merchandisers to act faster and with greater confidence — so they can show the right products to the right shoppers at the right time. Shoppers, in turn, benefit from smoother and more engaging product discovery journeys.
"Merchandisers are experts at retail strategy. They shouldn't have to waste their time doing menial investigations that AI can do for them," said Eli Finkelshteyn, CEO and co-founder of Constructor. "If a merchandiser has a great idea, we want to let them have AI do the execution. If a merchandiser gets a question about product visibility or campaign performance from their boss, MIA can give them the answer. If a launch happens and something doesn't look right, a merchandiser often doesn't have the time to investigate — they need answers now. MIA is here to help. And as Constructor's dashboard expands with more and more functionality, merchandisers shouldn't have to memorize where everything is. They should just be able to ask MIA."
Experience MIA at Shoptalk
Constructor is unveiling MIA at Shoptalk Spring today, during a live Product Showcase event:
Throughout Shoptalk, March 24–26, visitors can also stop by Booth #3255 to see live demonstrations of MIA and Constructor's other AI agents, and learn how Constructor's Commerce Reasoning Engine powers intelligent, adaptive product discovery experiences across the shopper journey.
For more information, please visit https://constructor.com/solutions/merchant-intelligence-agent.
About Constructor
Constructor is the AI-driven search and product discovery platform that scales, learns, and adapts to how shoppers actually buy. Its central reasoning engine uses reinforcement learning to improve with every shopper interaction — delivering the right product to the right person in the right context at the right time. By learning directly from real shopper behavior across a company's own properties, Constructor continuously drives stronger performance across the metrics that matter most. Purpose-built for ecommerce, Constructor generates consistent $10M+ lifts for leading brands such as Sephora, Petco, The Very Group, home24, Grove Collaborative and Fisheries Supply. Learn more at constructor.com.
SOURCE Constructor