Shantan Reddy, the AI lead for Gainsight, walks through how their AI features are built, with some practical tips and tricks for folks building with AI. He also shows some upcoming features they're building and their methodology for evaluating quality and building internal prototypes.

In this episode, Ankur and David discuss how RAG (retrieval augmented generation) technology works and why it matters. They build up a testbed example dataset and environment where they show code for how RAG works under the hood, how to evaluate the quality of results, why this technique matters, and where it can be applied.

You can browse a public version of the BrainTrust eval on the Coda help center content here: https://www.braintrustdata.com/app/braintrustdata.com/p/coda-help-desk

Here is the Open Source repository for the evaluation code and simple Next.js playground: https://github.com/braintrustdata/braintrust-examples/tree/main/help-docs/js

Check out more about the show at www.bitsandbots.ai

Parcha.AI founder and CEO AJ Asver shares practical lessons, prompts, and stories from deploying cutting-edge AI Agents.

Welcome to Bits and Bots, AI Builder Stories! In this first episode, co-hosts David and Ankur interview each other about their experiences building AI across various companies and startups. They discuss the lack of practical content for AI builders and their goal of sharing practical lessons learned. They also share their personal journeys in the field of AI, from Ankur's early interest in linear algebra and building a mini version of Google to David’s passion for AI and his work at Google and in gaming. They delve into their roles at Figma and Coda and how AI is being integrated into these platforms.