[Digital commerce & conversion]() / [Use cases]() / [Search platform choice]() [How it works]() [What you get]() [Scope]() [Start a review]() [Digital commerce & conversion]()[Search & discovery]() # Decide whether to keep, tune or replace your site search. An answer to “do we need a new search?” from your own queries and your own costs, not a vendor’s demo. [Start with a conversion review]() [How it works]() Right product first 200 judged queries - Current search, as configured **62%**Baseline - Current search, tuned **81%**Do first - Specialist search **84%**Costs more Fernway’s own queries, illustrative The same judged queries on each option. Tuning closed most of the gap. ## Sound familiar? - A vendor says search is why you’re losing sales. - Tuning the built-in search feels endless, and nobody has measured it. - You pay for search and for the people who patch it. A replacement costs months of integration and a contract. If tuning would have done the job, that was money and time you didn’t need to spend. ## What changes. ShowTodayWith the engine The question Which vendor is best? Does our current search clear our own queries? Evidence A demo on the vendor’s catalog Your catalog and your queries, side by side Cost The license fee License, setup, feeds, merchant hours and exit terms The default Switch The smallest approach that clears the bar ## How it works. 5 steps, 4 stages. - AI**1** - Rules and automation**2** - Your team**2** - Approval 1. 1 Judge 1. Your team ### Choose the queries that matter Your merchandiser and support lead pick real queries: exact codes, long-tail, misspellings, gifts. 2. 2 Compare 1. Rules and automation ### Run the same queries on each option Your search as configured, tuned, and the alternatives, on the same catalog on the same day. - Shopify - Algolia - Constructor 2. AI ### Score the results Each result judged against the right answer, with the misses grouped by cause. 3. 3 Cost 1. Rules and automation ### Price the whole option License or usage, integration, feeds, events, merchant hours and exit terms. 4. 4 Decide 1. Your team Approval ### Pick keep, tune or replace Your team decides on the evidence and the total cost. ## What you get. Real work, every week. Search options Effort or cost, first year - Keep and tune the built-in searchRules for codes and stock added **14 h**Do first - Move to a specialist platformThree points better on judged queries **Quote**Defer - Build a custom engineYou’d own relevance, models and upgrades **—**Not recommended The verdict for every option, with what it costs and what it leaves. ## How you’ll know it’s working. 1. Judged queries answered right The same queries, scored the same way, on every option. 2. Total cost of each option Setup, running cost and merchant hours, as well as the license. 3. Merchant hours a month What patching costs today, and what each option leaves. Baselines agreed before we build. ## Works with what you have. Commerce - Shopify - Adobe Commerce Search & AI - Algolia - Constructor We configure first Your platform’s own search is the first option to judge, and it isn’t a straw man. As of October 2026, Shopify’s Search & Discovery is free and Adobe Commerce includes Live Search. We build when The judged queries show a gap that tuning can’t close, and closing it is worth the cost. ## What a first build includes. Built in your accounts, around your team. Scope, fee and baseline agreed before we start. 1. 1 Design 2. 2 Build [Start with a review]() [Scope this build]() ### We build - A judged set of your real queries - A side-by-side run on each option - A total-cost model for each - A recommendation with a verdict for every option ### We start from - Search logs - Product catalog and stock - Your current search contract and settings ### From your team Owner Head of ecommerce Involves - Ecommerce - Merchandising - Engineering - Finance ## Questions teams ask. Will you recommend a vendor? Only if your own queries say a specialist is worth it. Tuning what you already have is often enough, and we’ll tell you when it is. When a specialist wins, we help you run the same test on matched proposals. What about open-source search engines? They can fit when you have engineers to own them. Their infrastructure bill isn’t comparable to a contract that includes merchandising tools and support, so we price every option on the same terms. Who owns it once it’s running? You do. It’s built in your accounts, documented, with training for the people who run it. Ownership usually sits with your head of ecommerce. We can keep running it with you, or step back. How do we start? Usually with a conversion review: two to four weeks, a fixed fee credited to the build, and a plan that’s yours. If the job is already clear, we can scope the build directly. ## Part of your conversion engine. One of 14 use cases, in 5 parts. [See the whole conversion engine]() 1. [Evidence & decisions **2**]() 2. [Search & discovery **2**]() 3. [Guidance **4**]() 4. [Cart & checkout **4**]() 5. [Releases **2**]() In search & discovery - [**Site search**Fix searches that miss the right product]() - **Search platform choice**You’re here Works with - [**Conversion diagnosis**Find what’s costing you sales, and what to fix first]() ## Choose search on your own queries. Start with a conversion review. [Start with a conversion review]() [**Talk it through first**15 minutes]() We reply within one business day. --- Source: [https://www.thekeating.co/use-cases/search-platform-choice/]() [Contact Keating & Co](mailto:nelson@thekeating.co) · [Agent guidance](https://www.thekeating.co/llms.txt)