Marketing Personalization
Black Eyewear wanted to capture elite styling expertise in AI so customers could get personalized eyewear recommendations and aspirational virtual try-ons without a long custom R&D cycle or a hard handoff between creatives and engineers.
Reported impact
Black Eyewear sped up AI feature delivery, extended in-store expertise into digital channels, and created a higher-polish try-on experience at far lower cost than earlier approaches.
Black Eyewear uses Google Cloud to address this challenge: Black Eyewear wanted to capture elite styling expertise in AI so customers could get personalized eyewear recommendations and aspirational virtual try-ons without a long custom R&D cycle or a hard handoff between creatives and engineers. Vertex AI Vision labels images and trains specialist models that evaluate facial structure and frame geometry, serving as the compute layer. Gemini Flash powers the conversational frame agent that interprets customer preferences and replicates Robert Roope’s styling voice, serving as the serving layer. Nano Banana 2 generates branded virtual try-on images from customer photos in seconds, serving as the compute layer. Gemini provides the multimodal reasoning layer that unifies vision, language, and recommendation logic, serving as the compute layer.
Customer preferences and uploaded photos enter the frame agent, Vertex AI Vision-derived models analyze facial geometry, Gemini Flash maps style cues into recommendations, and Nano Banana 2 renders branded try-on imagery for the shopper.
At the heart of the experience is a web-based frame agent, powered by Gemini Flash.
Nano Banana 2 generates try-on images in as little as four seconds, at a fraction of the cost of earlier solutions.
Using Vertex AI Vision, Robert and Tomas labeled thousands of images to train multiple specialist models.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Registered office address is Mercer House, 15 High Street, Redbourn, Hertfordshire, AL3 7LE.
Public company page lists company size 2-10 employees; page JSON-LD reports numberOfEmployees value 4.
Related
Google Cloud Sample Modified · Oct 9, 2026 Central Retail Food Replaced ~2,000 monthly manual Excel reports with a single source of truth on BigQuery through Looker dashboards Central Retail Food unifies its ecosystem on Google Cloud, moving from fragmented data to conversational… Addresses 50% to 60% of customer service queries with automated chatbots built on Conversational Agents BigQuery · Gemini · Gemini platform Google Cloud Sample Modified · Oct 9, 2026 ICA Previously, however, ICA’s fragmented technical environment was holding it back. Data was siloed across legacy platforms and SQL server environments, creating high maintenance costs and preventing teams from sharing… ICA Gruppen is a leading Swedish retailer, with a portfolio covering grocery, pharmacy and banking. Serving… BigQuery · Bigtable · Gemini Google Cloud Sample Modified · Oct 9, 2026 Purplle Purplle needed to support rapid 6x user growth, survive peak sale traffic, and automate search, CRM, pricing, and assortment decisions without increasing infrastructure costs or slowing down retail operations. 10x traffic spikes BigQuery · Cloud AutoML · Cloud Pub/Sub 