Engineering

Full-Text Search

I built search experiences over large product catalogues where keyword matching alone fails.

Used on

2021–2024

An AI search and document-assistant platform sold as Kray.AI, with a WooCommerce plugin and a demo store.

2024–2026

An AI product search for e-commerce stores that replaces the store's keyword search with intent and specification matching.

2023

Graph-backed e-commerce search over a mechanical-seal catalogue, for customers and staff finding parts by nomenclature, type or compatibility.

2023–2025

AI site search and chatbot for a caster manufacturer's e-commerce site, delivered under the Kray.ai product name.

2023–2026

Work that puts Kray, an AI e-commerce search product, into real stores: a store cloner, demo store and grocery rollouts.

2016–2021

SEO analysis product that crawls a customer site, analyses its pages and turns findings into assignable tasks for marketing teams.

2019–2020

A keyword research product that expands one seed phrase into a large, tagged keyword set with search-volume data.

2020–2023

A tool that shows who competes for a market in chosen locations and how visible each competitor is, for a market-intelligence firm.

2023–2024

A bot that shops on a major online retailer through a cloud browser, placing orders without a person at the keyboard.

2024 · Kray.AI search and document assistant

Situation: A document assistant for a fleet operator needed an architecture, and one model trained on every vessel's documents was the assumed default.
Task: Lay out the real trade-offs of cost, latency and access control instead of just picking one.
Action: I wrote both options out for client and team: one shared model versus one model per vessel, with pros, cons and the replica arithmetic.
Result: The partitioned design went forward, with the loss of cross-fleet questions accepted openly.