Swiggy Makes Decision Making Easier with its Generative AI Techniques

With the remarkable progress in Generative AI, the way customers interact with technology has undergone a significant transformation. 

The Bengaluru-based food delivery platform Swiggy has taken a lead in using generative AI techniques to build products and services to enable intuitive ordering experiences. 

“We understand that choosing what to order from the multitude of options available on our app can often be a daunting task. Swiggy has heard your feedback, and with neural search, we aim to alleviate this pain point and make decision-making a fun and effortless process,” shared Madhusudhan Rao, CTO, Swiggy in a blog post.

Swiggy’s neural search enables users to search using conversational and open-ended queries and receive recommendations tailored to their specific needs. This makes it easier for consumers to find what they’re looking for without having to use or remember specific keywords.

Imagine being able to type queries like, “I just finished my workout. Show me healthy lunch options,” or “Show me vegan-friendly starters” Swiggy’s neural search understands these open-ended, conversational queries and provide customers with personalized recommendations. 

The neural search capability has been built using a Large Language Model (LLM), adapted to understand the terminology related to dishes, recipes, and restaurants and Swiggy-specific search data. 

“We have 50 million-plus items in our food catalog covering a wide variety of options. Through a meticulous two-stage process, the model has been fine-tuned to respond accurately to relevant food-related queries, in real-time. These capabilities have been developed in-house, giving us greater control over the product, faster iteration time, and the flexibility to adapt to changing market trends,” added Rao

The brand is also building generative AI-led solutions to better serve their restaurant and delivery partners. 

“For example, we are piloting in-house tuned LLMs to empower restaurant partners to self-serve on processes and questions related to onboarding, ratings, payouts, etc, leading to faster issue resolution and streamlining. A conversational assistant powered by this LLM will be available in the restaurant-owner app and via WhatsApp,” he added.