E-commerce & Digital
Product image quality and consistency checking
Automatically review product images against style guide standards — background colour, shot angle, model consistency, shadow, and aspect ratio. Flags non-compliant images before they go live.
70–85%
reduction in manual image QA effort
Opportunity assessment
Minor improvement. Small efficiency gain with limited effect on overall turnover or bottom line.
Relatively straightforward. Off-the-shelf tools handle the core task. Implementation is well-understood with good examples to follow.
Light data requirements. Uses straightforward inputs — documents, product descriptions, customer records — that are usually accessible with minimal prep.
Low risk. Limited external exposure. A human reviews output before it reaches anyone outside the team.
Very easy to absorb. Runs quietly in the background or gives people a helpful new input. Makes everyday work easier with almost no friction.
Tooling required
Things to consider
Requires a clear, documented image style guide with specific measurable criteria — not just 'professional photography' but 'pure white background RGB 255/255/255, padding minimum 10% of image width, hero shot angle front-facing'.
Computer vision models for image QA are now accessible via APIs (AWS Rekognition, Google Vision, or multimodal LLMs) without custom model training for most standard checks.
Some style guide criteria (e.g. model expression, creative feel) are subjective and difficult to automate reliably. Focus automation on objective, measurable criteria and retain human QA for subjective ones.
Supplier photography is a common source of non-compliant images. If the QA system rejects a significant proportion of supplier submissions, the supplier brief needs improving — the QA system surfaces the symptom but fixing the brief at source reduces waste for everyone.
Experiment starter: Define five objective image criteria from your style guide. Use a multimodal LLM or computer vision API to check 200 recently uploaded product images against those five criteria. Compare the AI's flags against what a human QA reviewer would have caught. An 85%+ match justifies deploying the automated check in the product onboarding workflow.
Go deeper in the playbook
Section — Opportunity Identification, including the AI Opportunity Assessment ScorecardSection — The Tooling LandscapeThis is an automation opportunity — see the relevant playbook section for how to approach it.More in E-commerce & Digital
Product categorisation at scale
Automatically assign products to the correct site taxonomy categories using title, description, and attributes. Removes a bottleneck on new product onboarding.
Site search query analysis
Analyse search queries for intent, gaps, and failed searches. Identify where customers can't find what they want and prioritise catalogue improvements.
A/B test copy generation
Generate multiple headline, CTA, and banner copy variants for testing. Covers different value propositions, tones, and lengths with a single brief.
AI Transformation Playbook
Ready to assess your own opportunities?
The playbook gives you the full 150-opportunity directory, scoring tools, and 100+ templates for every stage of an AI transformation programme.