ecommerce_ops · ecommerce · workflow
Swiggy's generative AI year in review: catalog enrichment, review summarization, neural search, and restaurant partner RAG support
Swiggy needed to improve food catalog coverage through image and text description generation, reduce customer decision fatigue during ordering, and streamline dense FAQ navigation for restaurant partners, while managing generative AI risks including hallucination, latency, and data governance.
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 · Food image generation
A Stable Diffusion pipeline was integrated and customized to generate food images for catalog enrichment.
Tools used
Stable DiffusionLoRAGPT4OpenAI APILLMRAGNLUPythonvector databases
Outcome
Swiggy deployed generative AI across catalog image and text enrichment, review summarization, an AI content flywheel, neural search, and a restaurant partner RAG bot. A review summarization A/B test across over 2K restaurants showed improvements in funnel metrics and reductions in cancellations and claims. The restaurant partner bot was deployed to a subset of partners with promising initial results.
Results
Time saved~10–20 mins
Volumeover 2K
Running sincefirst quarter of 2023
Grounding & classification
Source type: technical build writeup
41 fields verified against source quotes.
content generationconversational aiknowledge searchragsummarizationknowledge baseproduct catalogsocial media postfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceautomation ratecustomer satisfactionemployee productivitythroughput increasetechnical build writeupcustomer supportecommerce opsmarketing opsdocument to recordrag answering