E-commerce search consulting that shoppers can feel
I built relevance for Walmart.com, the first Walmart Grocery search engine, and search at Shopify. I help online stores and marketplaces turn product search from a source of lost sales into one of their best-converting pages.
A good fit if…
- Your site search converts worse than browsing, and nobody can say exactly why.
- Shoppers search for products you sell and get zero results, or the wrong ones.
- Queries like "waterproof boots under $100" ignore the price, the attribute, or both.
- You added vector or "AI" search and lost the precision keyword search gave you.
Look elsewhere if…
- You're choosing between off-the-shelf search vendors and want a sales comparison. I measure and fix search; I don't resell it.
- Your catalog has a few hundred products. Good filters and navigation will usually do more than search work.
Deliverables your team keeps.
From brief to handover.
Pull your search logs and catalog. Find the zero-result and low-conversion queries that cost the most.
Build the evaluation set, diagnose each failure type, and size the fixes.
Ship fixes in order of revenue impact, starting with the cheapest: synonyms, attributes and filters before models.
Dashboards for search health and a playbook your merchandising and engineering teams can run.
Works with what you run.
What I've built before.
How it's priced.
Not sure where to start? Most teams begin with a fixed-scope search relevance audit.
Starting prices; the final quote depends on scope and follows a free intro call.
Remote, working with teams in the US, UK and Europe. Async-first, with live time during your Pacific mornings, or your morning and early afternoon if you're in Europe. Contracted and invoiced in USD through Infersense Labs LLC (Wyoming, USA).
Questions buyers ask.
Will this work on Shopify or our headless stack?
Yes. I've worked on search inside Shopify itself, and the methods apply whatever engine sits behind your storefront.
How do you measure the impact on revenue?
Offline relevance metrics on a labelled query set first, then A/B tests on conversion and revenue per search, so the business impact is measured, not estimated.
Do AI shopping assistants change any of this?
They raise the stakes. Agents send long queries full of constraints, like price, size and availability, which is exactly where weak query understanding fails. At Shopify I worked across the stack behind Sidekick, its AI assistant for merchants, mainly fine-tuning its LLMs.
What do you need from us?
Read access to search logs and the catalog, a contact on the engineering team, and someone who owns merchandising decisions.
Tell me what you're hiring for.
A free 30-minute call with me. You'll leave with a clear next step, and an honest answer on whether I'm the right person for it.