How AI Is Built  cover image

#014 Building Predictable Agents through Prompting, Compression, and Memory Strategies

How AI Is Built

00:00

Intro

Exploring the prompt compression technique to enhance predictability in large language models by shortening initial prompts. The chapter also introduces Taverly, a search tool that works with Lang chain agents to produce structured JSON outputs for easy database integration.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app