ecommerce_ops · saas · workflow
Popsa uses Amazon Nova and retrieval-augmented generation to deliver personalised photo book title suggestions at scale
Most Popsa customers are not professional copywriters and defaulted to generic titles like 'France 2024' or even just 'Photos'. The existing rule-based Title Suggestion Graph algorithm relied on templates and could not generate creative, personalised suggestions.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User selects photos, app extracts metadata
When users select photos for a Photo Book design, the mobile app reads metadata and runs on-device convolutional neural networks to extract relevant features.
Tools used
Amazon BedrockAmazon Nova LiteAmazon Nova ProClaude 3 HaikuConverseStream APIFastAPIconvolutional neural networks
Outcome
Switching to retrieval-augmented generative AI improved positive user feedback by 13% over the graph algorithm with Claude 3 Haiku, and Nova Pro further lifted satisfaction to 73% positive feedback. Migrating to the ConverseStream API cut time to first suggestion by 35%, and the feature generated over 5.5 million personalised titles in 2025.
Results
Time savedfrom 1.41 seconds to 0.92 seconds
Volumeover 5.5 million
Cost replaced13%
Running since2021
Grounding & classification
Source type: technical build writeup
39 fields verified against source quotes.
computer visioncontent generationpersonalizationragknowledge basemetric backednamed customerproduction runtime claimedproduction verifiedtools describedworkflow describedecommercesoftwareaccuracy improvementconversion increasecost reductioncustomer satisfactionresponse time reductiontechnical build writeupecommerce opsmarketing opsdata sync enrichmentrag answering