Our Early Journey to Transform Instacart’s Discovery Recommendations with LLMs Key Contributors: Moein Hasani, Hamidreza Shahidi, Trace Levinson, Guanghua Shu Introduction At Instacart, we are …

Instacart's resource offers insights, tutorials, and resources for shoppers and grocery delivery drivers. Readers can learn about grocery shopping tips, delivery strategies, and customer service best practices. With articles, guides, and tutorials, Instacart helps shoppers make the most out of their shopping experience and earn income through delivery services.

Instacart

Instacart's ML team shares how they rebuilt their Shopping Hub recommendation system using LLMs. The new AI-native platform uses a top-down, cascaded generation approach: a page design agent generates personalized themes from user context, a fine-tuned student model generates retrieval keywords via RAG, and quality/diversity filtering guards against off-brand or redundant content before passing to existing ranking infrastructure. Key techniques include teacher-student fine-tuning on Llama/Qwen models, RAG-based keyword candidate pruning (reducing generation costs 15-20%), and a fine-tuned DeBERTa cross-encoder for scalable quality filtering (99% cost reduction vs. LLM inference). Early A/B results are promising, with generative placements outperforming static baselines in offline evaluations. Key learnings: keep modeling tasks focused, invest heavily in evals, and add structure to input/output layers.

Our Early Journey to Transform Instacart’s Discovery Recommendations with LLMs

Get Moein Hasani ’s stories in your inbox

Designing for Rapid Iteration: Treating Evals as a First-Class Citizen