The first version of this system took 40 minutes to process 200 customers and sometimes recommended beers that didn't exist. The current version handles 400 customers in 13 minutes, and every recommendation is real and fits the customer's taste. The fix wasn't a better AI model or a smarter prompt. With each version, I gave the AI less to do.
The client. A startup that delivers curated beers to customers' doorsteps. Its core promise is that each customer gets picks matched to their taste. Personalisation isn't a feature for them; it's the product. I'd already built their SMS subscription platform, so I knew their data and operations well.
The problem. Every customer was matched to the right beer by hand, and that didn't scale as the customer base grew. The client wanted it automated without losing the personal touch customers pay for.
What didn't work, and why. The first version was a deliberate proof of concept. We gave an AI agent the full catalog and each customer's preferences and asked it to do the matching end to end, to see whether AI matching was viable at all. It worked well enough to justify going further. Running it across about 200 customers showed where it broke down: a run took around 40 minutes, matches often missed what customers liked, and the agent sometimes recommended beers that didn't exist. For a curation business, those gaps hit the product directly.
The second version narrowed the options before the AI saw them. That was better, but the matches still weren't reliable enough to send to customers.
What worked. Each new version gave the AI less to do. Matching moved out of the AI's judgment and into a structured system built around the client's own data and business rules. In the current version, that system does the heavy lifting and narrows every customer down to their three strongest matches. The AI's role is narrow: it picks the final beer from those three and writes the one-line reason the customer sees.
The result. 400 customers processed end to end, recommendations and offers, in 13 minutes. That's twice the customers in a third of the time. The recommendations reflect what each customer actually likes, there are no invented products, and the system costs less to run because the AI handles one narrow step instead of the whole job.
"The business now has a clear path to scale and at less cost because we aren't spending endless tokens on Frontier models."— Founder, curated beer-delivery startup
The lesson. When AI disappoints, the fix is rarely a better prompt. It's the structure underneath: clean data, clear rules, and AI used only where judgment is genuinely needed. That's the work I do. I build the operational foundation that makes AI reliable, then the AI on top of it.
If you have an AI project that isn't delivering what you hoped, I'd be glad to take a look. Get in touch
Built with Airtable, Lovable, and a background job pipeline (earlier versions in Make).
Written by