Live
Our generative product-photo and video studio · Gemini on Google Cloud
- Generative AI
- Gemini
- Google Cloud
Retail and e-commerce · Content and media
Catalogue and content factory
Batch-generate product descriptions, attributes, alt text, translations and on-brand imagery for thousands of SKUs with Claude and Gemini, with a human review queue.
- ClaudeAnthropic
- GeminiGoogle
- Typical timeline: 2–4 weeks
The problem
Thousands of SKUs with thin descriptions, missing attributes, no translations and inconsistent imagery hold back search visibility and conversion.
- Copywriting can't keep pace with new SKUs.
- Attributes needed for filters and marketplaces are missing or inconsistent.
- Product photos vary in background, crop and quality.
How we solve it
A batch pipeline that writes schema-valid product content in your brand voice, cleans up and varies product imagery, and routes anything sensitive to a reviewer before it is published.
It plugs into Shopify, WordPress / WooCommerce, Google Drive and Product spreadsheets, so nothing you rely on today is replaced. The architecture below shows each step and which model does the work.
Architecture
From your stack, through the AI layer, to numbers you can track
Each step names the model or system doing the work. Writes to your systems wait for a person to approve them.
Your stack
- Shopify
- WordPress / WooCommerce
- Google Drive
- Product spreadsheets
AI layer
Softpiper AI layer
- Claude
- Gemini
- Pull the catalogue, using Shopify Admin API · WordPress MCP
Products, existing copy and images are exported from Shopify's Admin API or WordPress, along with your brand guide and an attribute schema per product type.
- Write the content, using Claude Sonnet · Batches
Descriptions, attributes, alt text and translations are generated in batches, with the brand guide in a cached prefix and structured outputs enforcing the schema.
- Improve the imagery, using Nano Banana image models
Backgrounds are cleaned, lifestyle variants created and banner text rendered.
- Score against the brand, using Claude reviewer
A reviewer pass scores every item against your rubric and flags regulated claims for a person.
- Review and publish, using Review queue
Approved items are written back to the store; rejected ones return with the reviewer's notes.
Outcomes you measure
- Catalogue completeness (share of SKUs with required attributes)
- Time to list a new SKU
- Organic impressions and click-through trend
- Return rate on items with rewritten descriptions
Why this model
Claude and Gemini, each where it leads
We choose per task on capability, cost and where your data must stay. Final versions are picked at kickoff.
ClaudeAnthropic
Claude writes in a defined brand voice and returns structured output that matches a JSON schema per product type, so every SKU arrives with the same fields. The Message Batches API halves the cost of large runs, and a second Claude pass scores each item against your brand rubric.
GeminiGoogle
Gemini's Nano Banana image models handle background clean-up, lifestyle variants and legible text on banners. LuxeLens, our own product-photo studio, is built on Gemini image models.
Delivery
What you get, how long it takes, and how we keep it safe
Guardrails
- Regulated claims (health, cosmetics, safety) always go to a human reviewer.
- Nothing is published without passing schema validation.
- AI-generated imagery is disclosed where marketplace or local rules require it.
- Original copy and images are kept, so any change can be rolled back.
Plus the guardrails on every build: facts from your systems, approvals for writes and money, a human one step away, audit logs and evals. See all
Deliverables
- Batch pipeline with a schema per product type
- Brand-voice and rubric prompts
- Image clean-up and variant workflow
- Review queue with write-back to your store
- Cost-per-SKU report
Typical timeline
- Pipeline and first batch2–4 weeks
A planning range for a first production release. We confirm scope, price and dates in a tailored proposal.
KPIs to track
- Catalogue completeness (share of SKUs with required attributes)
- Time to list a new SKU
- Organic impressions and click-through trend
- Return rate on items with rewritten descriptions
- Cost per SKU enriched
Goals we agree with you and measure from a baseline. They are what we track, not results we promise.
Related services
The services behind this playbook
AI product engineering
From prototype to production: RAG, copilots, multimodal features and the evals that keep them honest.
View serviceE-commerce
Storefronts with character that load fast, convert on mobile and run on payment rails your customers trust.
View serviceData and automation
Turn scattered data and repetitive work into dashboards, pipelines and reviewed automations.
View service
Our work in this space
What we've built for retail and e-commerce
Sites and products we've shipped for businesses in this sector. They show how we work; they are not deployments of this playbook.
LiveShopify e-commerce, built and managed end to end · Premium apparel from India
- E-commerce
- Shopify
- D2C
More playbooks
Related playbooks
Retail and e-commerce
AI shopping concierge for web and WhatsApp
Shoppers leave when they can't get a fast answer on sizing, stock, delivery or returns, and your team answers the same questions across chat, email and WhatsApp.
- Claude
- Gemini
- Typical timeline
- 3–10 weeks
- Plugs into
- Shopify · WhatsApp Business · HubSpot or Zoho CRM +1 more
Media and entertainment
Booking concierge and promo content engine
Cinemas and venues field the same showtime, seat, food and offer questions all day, while marketing needs posters, thumbnails and short promos for every title and city.
- Claude
- Gemini
- Typical timeline
- 4–10 weeks
- Plugs into
- Ticketing / POS system · WhatsApp Business · Website (WordPress or Wix) +2 more
Real estate
Lead qualification and property-matching concierge
Portals and ads bring high lead volumes, follow-up is slow, and agents spend their time on enquiries that were never going to buy.
- Claude
- Gemini
- Typical timeline
- 4–10 weeks
- Plugs into
- HubSpot or Zoho CRM · Salesforce · Listings database +2 more
Pip · Softpiper's AI
Ask Pip about this playbook
Ask Pip how this would work for you
Pip is Softpiper's AI. Tell it what you run today and it will walk through how this playbook fits, what we would build first and a tailored price range. Or book a call with the team.