AI Agents for Unbxd
Published 1 July 2026, 11 min read
Context
Unbxd is a software that powers the search bar and recommendations behind E-commercesites. When you search for something and the results actually make sense, that's this working. It handles this at a massive scale too, tens of billions of searches a month. And it responds in under 10 milliseconds, basically instant.
Logo: Netcore UNBXD
The Problem
As an e-commerce search optimisation company, we've seen a few issues persist for over a year, ones that needed real restructuring and new experiences to fix. Solving them meant first understanding the data well enough to act with confidence. We chose to fix these 3 problems first because they affected the majority of our users. Here are the three problems we set out to solve.
Repetition became the real bottleneck.
Boosting a product for a sale meant the same routine every time: pick it, set the promotion type, choose how long it runs, all by hand, across multiple screens. It wasn't hard, it was just repetition of the same steps every time.
Caption
Search performance lived across several separate reports, so understanding last week meant juggling all of them yourself, there was no plain-language summary to just ask for instead.
Caption
A product could get plenty of clicks and still rank low, and there was no way to know why. Just a debug panel full of numbers, and no answer.
Goal
Once we saw where the patterns kept pointing, we picked a direction for each one, three problems, three directions. What follows is where we decided to aim.
Caption
Right now, each promotion has to be created on its own, one at a time, even when you need many of them. The goal is to create several promotions together, with far less effort than doing them one by one.
Caption
Promotion reports are just numbers in a table, with the important part buried inside them. The goal is to pull that out, turn it into plain sentences, and highlight what matters most.
Caption
A listing can underperform for more than one reason: the words don't match what shoppers search, or the system doesn't understand what they meant. The goal is to make that reason visible, and point toward something worth trying.
Our Approach
The direction we landed on
Competitor analysis, user interviews, research, all of it pointed to the same place. The industry had already set the baseline — AI agents.
People had already started leaning on AI tools in their everyday work, without anyone telling them to. That quiet shift meant expecting a plain conversation to get something done wasn't unusual anymore, it was becoming normal.
We saw competitors already shipping AI-assisted tools for search and merchandising, and getting real results from them. This wasn't an emerging trend anymore, it had already become close to a baseline expectation rather than a differentiator.
Constraints
- We wanted one assistant to do all three jobs. The company's data was too scattered across systems for one assistant to make sense of everything at once, so we built three separate assistants instead, each doing one job.
- Each assistant only knows about the page you're currently on. If you're looking at shoes and ask about socks, it can't answer, because it has no visibility outside the page you're viewing.
- You can only use one assistant at a time. You can't have two working on two different things at once.