Independent Build — AI Recommendation Tool
Shifting the Burden of Product Knowledge From the Customer to the Tool
Choosing a product shouldn’t take a materials degree. SkegJev turns a plain-language description of your surfing into the fins that fit.
Case study details
The Challenge
If the knowledge burden sits on the customer, then people will default to the safest choice. That’s the gap: between what the customer knows and what the page expects them to know.
I call it knowledge fatigue, and it isn’t a surfing problem. It’s the same wall you hit choosing a kitchen sink or picking a plant for a dark corner. The right answer is somewhere in the catalog. The customer runs out of energy before finding it. Everyone loses: the customer settles for something that fits worse, and the business misses the sale of the product that would have fit better.
I ran into it myself with fins. I’ve surfed my whole life, and choosing fins still overwhelms me.
There are dozens of sets, each in several materials and sizes. The differences live in words like “Performance Core Carbon” and “Accelerator template.” I’ll read for ten minutes, feel less sure than when I started, and buy the standard set. The people I surf with do the same.
FCS has great information: descriptions, size charts, a construction guide. But it’s static. It expects you to read and understand every nuance of each material and use case, then match that to your own board, waves and style.
Here’s what I do know:
- my board
- my weight
- the waves I surf
- what I want to feel
What I don’t know is what “Performance Core Carbon” means for me.
The Approach
The Idea — This build is about using Jev to create a better experience for the person on the other side of the screen. You tell it what you know, in your own words, the way you’d tell an expert at a surf shop. It works out what matters and narrows the options as you type, and you go back and forth until you land on the right one. It’s not a quiz and not a form. It’s a natural conversation that ends at the right product.
That conversation works anywhere a person knows their situation but not the product vocabulary:
- For a course: “I manage a small team, I’ve got an hour a day, and I’ve never touched data.”
- For cabinets: “Small galley kitchen, two kids, I cook every night.”
How It Works — I built it around fins, so I’ll use fins as the example. You type something like “5’10" Secret Agent, 175 lb, punchy beach break, more release.” A language model turns that into facts about your board, weight, waves and goals. It only understands what you said. It never picks the fins. The options come from FCS’s own product data (their descriptions, ideal conditions and size tables), and clear rules match them to you. Jev, a semantic scoring tool from TypeSafe, helps read your situation against the closest few options. The answer comes back in plain English: why this one, what size and material for you, and what you give up. Change any answer and the picks update.
The structure is the same for any catalog:
- A person describes their situation in plain words.
- A model pulls out the facts.
- Clear rules match those facts to the catalog.
- The answer comes back with reasons.
How It Got Better — My own use shaped it. I dropped questions that didn’t apply, made the live picks match the final picks, let you edit any answer, and held off ranking until there was something to rank on. Reading FCS’s own guide also corrected my assumptions about materials and ability, and the tool’s material picks now follow it. Those lessons carry over to any product: only ask what matters, and let people correct what you heard.
The Results
Anyone can now find products that fit them without knowing anything about the materials and nuances. A few plain details about themselves and how they’ll use it can guide them to the best-fitting product.
In my case, that was fins. The profile was a 5’10" Secret Agent, 175 lb, punchy beach break, and “more release.” It pointed me to:
- Best overall: FCS II Reactor, Medium, Performance Core. It’s strong on easy release, suits beach-break conditions, and Medium is the closest size for 175 lb. What you give up: some grip when you push hard and drive through turns.
- Also a strong fit: the CI Upright, a close cousin of the Reactor.
- The different-feeling alternative: the Sharp Eye in PC Carbon, for smooth flow. It trades some steadiness and grip, and the stiffer material can feel harsh for lighter surfers.
That pushed me toward a performance-level fin I would likely have skipped for the safe standard one. For a business, the same shift means fewer customers quietly settling for the familiar option, and more of them buying the better-fitting product, often a higher-value one.
See It In Action
The Takeaway
Fins are just the example. Any product where the sale depends on what the customer already knows has this problem: wetsuits, mattresses, cameras, bikes, skincare, software plans, courses.
Left alone, that uncertainty pushes people to the safe, familiar choice. That’s where I would have landed: the standard set. A tool that takes the uncertainty away lets them choose what actually fits, and that can be a better product and a higher-value one. This is how companies can begin to remove the knowledge burden from the customer and let their tools do the heavy lifting.
SkegJev is an independent project and isn’t affiliated with or endorsed by FCS. Fin descriptions, size tables, prices and availability come from FCS’s public product pages.