Shopify Magic and Sidekick configured properly. Custom OpenAI, Anthropic Claude, and Google Gemini builds — AI search, recommendations, conversational commerce. GDPR-safe, cost-capped, A/B-tested.
BRAND MARKS © THEIR RESPECTIVE OWNERS · WE BUILD ON THESE PLATFORMS, WE'RE NOT AFFILIATED WITH THEM.
Shopify Magic generates brand-aligned product descriptions in minutes — and the lift on PDP CR is measurable. We configure Magic with your brand voice and roll it across the catalog.
AI search (Algolia AI, Klevu AI, or custom OpenAI embeddings) understands intent — "warm winter coat" returns the right products, not just keyword matches. Average 15-30% lift in search-to-conversion.
Rules-based recs cap at the patterns in your purchase data. LLM-driven recommendations handle cold-start, semantic similarity, and bundle reasoning. Better in beauty, fashion, B2B.
An AI triage layer on Shopify Inbox handles 40-60% of tickets without human handoff — order status, shipping ETAs, returns, sizing. Trained on your help docs and order data, with human escalation for anything sensitive.
Custom AI features (shade-finder, fit predictor, configurator) lift category-specific CR meaningfully. We have shipped these on Hydrogen + Plus stores in beauty and fashion.
We build public AI apps end-to-end — Polaris admin UI, embedded chat, OpenAI / Claude backend, Shopify-hosted billing. Currently one in App Store review.
Where AI earns its keep on your store. We benchmark Magic vs custom, recommend a model (OpenAI / Anthropic / Gemini) per use case, and produce a token-cost projection.
Data-flow diagram. PII redaction layer. Vector store + RAG (where applicable). Cost caps + observability. DPA drafted.
Functions, custom app, or Hydrogen layer — depending on the use case. Local prompt tuning, output evals, deterministic fallbacks for when the model is slow or down.
Every AI feature ships behind a flag and runs against a non-AI baseline for 14 days minimum. We only ship features that lift conversion or AOV with statistical significance.
Production rollout with full observability. Monthly token-spend report against projected vs actual. Quarterly model review (price drops, new releases, switching opportunities).
Live, monitored, cost-capped. In your Shopify org.
Reusable across Magic, custom apps, and future features.
PII never leaves your infrastructure unredacted. Documented.
Per-request token spend, broken down by use case. Predictable.
Statistical proof the AI variant beats the baseline.
How to benchmark a new model against your existing one.
Shopify Magic + Sidekick + Inbox AI configured for your store. Native AI tools, set up properly.
Custom OpenAI / Anthropic / Gemini integration. AI search, recommendations, generative content, or conversational commerce.
Bespoke AI Shopify app — public or private. Polaris admin UI, embedded chat, full LLM stack.
It depends on the job. OpenAI for generative content and structured output (most product description tasks). Anthropic Claude for long-context tasks like catalogue-wide reasoning and complex customer-service triage. Google Gemini for multimodal (image + text) and where pricing matters. We benchmark on your actual data before committing.
Token-cost projection is part of every quote. In production we cap per-request token budgets, cache aggressively, and use prompt distillation (smaller models for simpler tasks). Most clients run AI at under £500/month total spend; high-volume clients with conversational commerce run £2,000–£8,000/month with clear ROI tracking.
For stores under ~500 SKUs with simple content needs — Shopify Magic is usually enough. Our Magic Config tier (£999) is a one-week setup that gets you brand-aligned product descriptions and email subject lines. Above 1,000 SKUs, custom integrations earn their cost via measurable PDP conversion lift, AI search lift, or service-cost reduction.
PII is redacted before any external LLM call by default. Where personal context is needed (CS triage, conversational commerce), we use the provider's zero-data-retention enterprise tier or run inference locally on your infrastructure. Every AI integration ships with a DPA and a data-flow diagram.
Yes — that is the Custom AI App tier (£14,999+). We handle Polaris admin UI, embedded chat, OpenAI or Claude backend, Shopify-hosted billing, App Store review compliance, and submission. Typical build is 6–10 weeks plus 2–6 weeks of Shopify review.
Sidekick is built into Shopify admin and works out of the box for most stores. Explicit configuration earns its keep on Plus B2B stores with custom catalogues, multi-store organisations, and stores with complex Functions — we tune Sidekick prompts and document workflows for your team during a 1-week sprint.
Yes. Three approaches: Algolia AI (drop-in, fastest, expensive — best for £500k+/month stores), Klevu AI (mid-tier pricing, strong for apparel and home), or custom OpenAI embeddings + pgvector (most flexible, lowest run-rate cost, requires our middleware). Most stores see 15–30% lift in search-to-conversion.
Yes — conversational commerce with AI triage on Shopify Inbox handles 40–60% of low-value tickets without human handoff (order status, shipping ETAs, returns, sizing). Trained on your help docs and order data, with human escalation for anything sensitive. We do not deploy AI chat on regulated categories (supplements, wellness with claims).
Yes — typically using LLM-driven recommendations layered on top of rules-based recs (LimeSpot, Rebuy, Nosto). LLM recommendations handle cold-start (new products with no purchase history), semantic matching ("looks like this but in green"), and explanation copy. Average uplift on click-through is 18%.
Tell us what you want AI to do — generative content, AI search, recommendations, conversational commerce, custom features. We come back with a fixed scope, a model recommendation, and a token-cost projection.