HOLLOW POINT
Contact
Get In Touch
Dubai: +971 588130712UK: +44 7814173588hi@hollowpoint.io
AI ENGINEERING · FORWARD DEPLOYED/ ai-engineering

AI engineering for Shopify Plus operators.

Forward-deployed engineering for £1M+ stores. We build the Claude agents, MCP servers and Claude Code skills that run our own Shopify Plus business — and deploy the same stack to clients in 8 to 12 week embedded engagements.

Multi-£mOwn Shopify Plus stores under managementoperator-built
7,000+Variants touched — created, edited, repriced, retagged
200+Collections with content we wrote, rewrote, optimised
8–12 wksEmbedded build, fixed scopeno retainers
§ 00  —  OPERATOR BRIEFcase summary
MODEL
Forward deployed engineering (FDE)
Palantir-origin
CLIENT FIT
Shopify Plus, £1M+ annual revenue
UK + EU primarily
STARTING SCOPE
Embedded 8–12 week build, fixed price
—
ENGAGEMENT RATE
From £8k–£15k / month embedded period
depends on scope
OWNERSHIP
Client owns code, prompts, schemas at the end
—
OPEN SLOTS
One engagement opens every 6–8 weeks
limited capacity
§ 01  —  POSITIONING

We don’t sell AI. We run on it.

Most agencies pitching “AI for ecommerce” are bolting GPT wrappers onto retainers they were already selling. We took the other path. We’re operators. We run a multi-£m Shopify Plus store as our own business, and we built a stack of Claude agents, custom MCP servers and Claude Code skills out of necessity — to run that store with fewer hands and better decisions than agencies could deliver.

Then clients started asking us to build the same thing for them. So now we do both: we run our store, and we ship the same engineering to other operators in fixed-scope engagements.

When you hire us, you're not hiring a team that talks about AI. You're hiring the people who built the systems they use every day, and who'll build yours the same way.

——
§ 02  —  WHAT WE'VE BUILT

Six systems we ship and use in production.

These sit on top of broader catalogue work — every one of our 7,000+ variants has been touched in some way. Products created from supplier specs, existing products edited and retagged, meta titles rewritten across hundreds of pages, collection content authored and optimised.

01

Merchandising triage agent

A variant-level Shopify clearance system using Claude Sonnet plus a custom MCP server against the Shopify Admin GraphQL API. Pulls 90-day sales velocity per variant, applies a rule we landed on after some painful learning — only clearance-tag a product if every variant is slow, cut only the slow variants if it’s mixed — and writes the changes back through GraphQL. One day, 248 SKU lifecycle decisions, variant-aware. 47 hardware, 201 e-liquid. The same job used to eat ~40 hours a week of merchandiser time.

02

Catalogue operations engine

A Python agent against the Shopify Admin GraphQL API for any workflow involving the same operation across hundreds or thousands of variants. First job: cost-update run across 7,000+ variants — 83% coverage in one shot. Since then: bulk metafield writes for SEO content blocks, meta title and description rewrites across hundreds of pages, redirect imports, price-rule application, attribute normalisation, product creation from supplier spec sheets.

03

SEO content sub-agents

Custom Claude Code agents for collection rewrites and product descriptions. Each one is brand-voice tuned, fed structured input from Ahrefs and GSC, and writes output that meets our internal SEO checklist — primary keyword in H1 and first paragraph, semantic variations, FAQ blocks where they fit, internal links to sibling collections. Used daily across 200+ collections on our own store. Editing time roughly 80% less than writing from scratch.

04

Custom MCP servers

In-house MCP servers connecting Claude to:

  • Shopify Admin GraphQL (variants, metafields, metaobjects, redirects, bulk ops)
  • Ahrefs (keywords, ranking, SERP overview, competitor research)
  • Google Search Console (queries, pages, performance)
  • Sanity (content + records from the property finance build)
  • Internal merchandising data store (sales velocity, stock, supplier data)

We’re open-sourcing one of these soon.

05

Claude Code skills library

A library of in-house Claude Code skills covering the workflows we run weekly:

  • Collection creation and content upload
  • Shopify product listing imports (pasted supplier data → listed products)
  • Weekly merchandiser reporting
  • Clearance triage
  • Content writing for collection and product pages
  • SEO content optimisation + competitor analysis

Skills turn an ambiguous request into a deterministic workflow.

06

Property operations platform

Outside Shopify entirely. End-to-end Next.js + Sanity + Vercel platform managing a multi-property residential portfolio for a UK property operator. Liaison packs, fire and safety logs, evacuation plans, incident reporting. Live in production, used daily by the operations team. Full write-up.

——
§ 03  —  THE FDE MODEL

How forward-deployed engineering works for ecommerce.

Most agencies sell hours. The forward-deployed engineering model is different — and it's the model we run.

A forward-deployed engineer (FDE) embeds with a customer, owns a problem end-to-end, and ships production software inside the customer’s environment. The role started at Palantir, scaled at companies like Anthropic, OpenAI and Sierra, and is now becoming the standard way technical AI work gets delivered. It works because most enterprise AI deployment isn’t a model problem — it’s a context problem. You can’t deploy useful AI without deeply understanding the workflows, constraints and edge cases of the business you’re deploying it into.

The same logic applies to Shopify Plus. Plugging a generic AI tool into a multi-£m store and expecting it to work is the same mistake enterprises made in 2023. What actually moves the needle is someone who sits inside your business, understands your catalogue, your customers and your operations, and ships the systems that fit your specific reality.

We're a small consultancy that operates like an internal FDE team — embedded, accountable, shipping working code, not deliverables in PowerPoint.

——
§ 04  —  ENGAGEMENT MODEL

Three phases, fixed scope, no retainers.

We work in 8 to 12 week embedded builds. Fixed scope, fixed price, agreed up front.

01

Weeks 1–2 · Scope and embed

Full read access to your Shopify Admin, GA, GSC, Ahrefs, and any internal tooling. We sit in your Slack or Teams. We talk to whoever owns merchandising, customer service, ops. By end of week 2 we’ve identified the two or three workflows that, if AI took them over, would compound the most over the next year. We agree the scope in writing.

02

Weeks 3–8 · Build and ship

Most weeks we ship something. The first thing usually goes live by week 4 — a small agent doing real work on real data. From there we layer in additional workflows, custom MCP servers if needed, and integration into your existing tooling. You see weekly demos, not monthly status reports.

03

Weeks 9–12 · Hand off and document

The systems we built are owned by you. We document everything — architecture, prompts, schemas, runbooks. We train your team. We agree what ongoing optimisation looks like, if any. We’re not interested in retainer dependency. After week 12 you have production AI systems running in your business that you understand and own.

——
§ 05  —  WHAT WE DEPLOY

The technical stack, every engagement.

Open standards where possible. Custom code where it actually matters. Nothing locked behind our toolchain.

Coming soon, open-sourced: hollowpoint/shopify-mcp-server and hollowpoint/claude-skills-shopify.

stack.config
→Models:        Claude Sonnet 4.6, Opus 4.7, Haiku
→Orchestration: Claude Code + custom Python / TS
→Shopify:       Admin GraphQL (variants, MF, MO, bulk)
→Data:          GSC, Ahrefs, internal DBs
→Infra:         Vercel, GitHub, your existing tools
+Custom MCP servers: in-house, client-owned
+Skills library: in-house, client-owned
——
§ 06  —  FREQUENTLY ASKED7 entries

Things operators actually ask before signing.

——
hollowpoint.io / contact

operator@hollowpoint:~$cat next-step.txt

Book a discovery call.

Tell us about your store and where AI engineering would help. 30-minute call, no pitch. Either we tell you yes we can help and here's what an engagement looks like, or no this isn't a fit and here's what we'd do instead.

Talk to us Grab a 30-min slot
related —AI ops case study/case-studies/about