AI & Machine LearningGisting: Compressing LLM Agent context to ↑ throughput and ↓ costGisting compresses context into a set of learned tokens, preserving its quality while making the model faster and cheaper.by Cody Mazza-Anthony / Paige VegnaAug 19, 2026
AI & Machine LearningSidekick's continual learning loopby Andrew McNamara / Cody Mazza-AnthonyAug 5, 2026
AI & Machine LearningClustering billions of products for agentic commerce with Catalog APIJun 17, 2026
AI & Machine LearningTeaching Sidekick to say no: automated data curation with LLM judge consensusJun 15, 2026
Data Science & EngineeringShopifyQL Notebooks: Simplifying Querying with Commerce Data ModelsFeb 14, 2023