AI Shopping Feeds takes a product catalogue, rewrites titles and attributes with AI, checks every feed against each channel's rules and exports it to 200+ shopping channels. I built it over 12 months.
I spent years managing Google Ads accounts on almost every feed management tool going. Each one did some things well, but there was always a feature or two missing that we needed, so the team worked around the gaps by hand.
So I built our own for my team at my previous agency, covering every feature we'd ever needed: multi-country feeds, a proper rule engine, and AI built in from the start to automate the tedious feed work. It's since grown into a SaaS of its own.
Import, optimise, automate, export. The platform also includes a DPA creative editor for branded product creatives and performance labels that tag products by how they sell.
Bulk-rewrites titles, descriptions and categories in the brand's voice, giving Shopping and Performance Max stronger data to rank on.
IF / THEN rules that run on every feed refresh: capitalise titles, drop test products, add brand prefixes, normalise sizes. Priorities, dry runs, per-brand scope and a full change history.
Every feed gets a 0 to 100 health score against Merchant Centre, Meta and TikTok specs, with one-click fixes and daily audits that alert by email and Slack.
One login for every brand and every country, each with its own rules, exports and credits. One-click Shopify connect or CSV, XML and JSON in; Google, Meta, TikTok, Microsoft, OpenAI Commerce and the rest of the 200+ channels out.
Product views from aishoppingfeeds.com. The brand names in them are demo data.
A top-level look at how it's put together. The short version: it's built to handle thousands of products and channels without falling over.
A single-page app for managing feeds, rules and audits. The feed audit runs in the browser and scores a catalogue from 0 to 100 across eight categories.
Every product, feed and rule belongs to a team, with roles and brand-level permissions enforced right down to the database with row-level security.
Bulk AI runs, feed refreshes and channel syncs run as background jobs on a database-backed queue. Jobs save progress as they go, and locks let several servers share the work without doubling up.
Titles and attributes are rewritten with strict structured outputs, and models can be swapped on price. Credits are reserved before each call and settled on the result, so a retry never charges twice. Low-confidence picks are left blank, not guessed.
Imports from Shopify, WooCommerce, BigCommerce, Magento and spreadsheets. Pushes to Google Merchant Center and Meta catalogs, with streaming CSV, XML and JSON exports for every other channel.
Dockerised services behind Cloudflare, with file storage on R2, caching tuned per endpoint, request timing on every call, and Stripe and Shopify billing.
I've spent 7+ years in paid advertising, agency-side and in-house, most recently as Head of Paid Search for 3+ years at Soar With Us, a D2C agency, growing brands to 8+ figures. I've since started Pavegrowth to continue my love of building and growing brands with that expertise.
Alongside the ad accounts I build Shopify themes, iOS apps and software products, including my own. Growth marketing and development under one roof. I utilise AI workstreams to support moving faster & streamlining internal & client workflows to ensure efficiency, whilst the strategy, judgement and accountability are mine. You talk directly to the person doing the work.
Thirty minutes to get to know your brand, your goals and where the growth is. No pitch deck, just a straight conversation about where we'd take it next.
I'll get back to you shortly about your request. Looking forward to learning more about your project & goals!
