Episode 51 - Swiggy - Improving search relevance in hyperlocal food delivery using (small) language models

Episode 50 - Swiggy’s Generative AI Journey: A Peek Into the Future

Episode 49 - How Salomatic Uses DSPy & Langtrace to Build a Reliable Medical Report Generation System

Episode 48 - Speak.com's Live Roleplays powered by OpenAI Realtime API

Episode 47 - How Meta animates images at scale

Episode 46 - Hermes: A Text-to-SQL solution at Swiggy

Episode 45 - How Meta trains large language models at scale

Episode 44 - The secret ingredient in Continue's autocomplete prompt

Episode 43 - Dropbox - Bringing AI-powered answers and summaries to file previews on the web

Episode 42 - ColPali: Efficient Document Retrieval with Vision Language Models

Episode 41 - How Headstart built a mobile app in a day with Claude.

Episode 40 - DoorDash's path to high-quality LLM-based Dasher support automation

Episode 39 - Emerging Architectures for LLM Applications

Episode 38 - How companies are bringing AI applications to life

Episode 37 - Scaling Productivity with Ava — Instacart’s Internal AI Assistant

Episode 36 - How Graphite uses GPT to optimize code reviews

Episode 35 - How Salesforce built XGen, their LLM

Episode 34 - How Salesforce's Einstein 1 Platform Manages Massive Data and AI Workloads at Scale

Episode 33 - How Salesforce operationalizes Models at scale

Episode 32 - How Pinterest built text-to-sql