Principles of Building AI Agents (ft Sam Bhagwat)
カートのアイテムが多すぎます
カートに追加できませんでした。
ウィッシュリストに追加できませんでした。
ほしい物リストの削除に失敗しました。
ポッドキャストのフォローに失敗しました
ポッドキャストのフォロー解除に失敗しました
Principles of Building AI Agents (ft Sam Bhagwat)
-
ナレーター：
-
著者：
このコンテンツについて
Join the Tool Use Discord: https://discord.gg/PnEGyXpjaX
Building AI agents is the current trend, but are you doing it correctly? Sam Bhagwat, founder of Mastra, joins Tool Use to breakdown the principles of building reliable AI agents. We discuss why you should use a TypeScript agent framework like Mastra, how to engineer production-grade prompts, and the best patterns for tool calling. Sam explains advanced concepts like observational memory, dynamic agents, and the "lethal trifecta" of security risks. Whether you are building coding agents or enterprise workflows, this episode covers the essential primitives for success.
Mastra: https://mastra.ai/
Get the Book: https://mastra.ai/book
Connect with us
https://x.com/ToolUsePodcast
https://x.com/MikeBirdTech
https://x.com/calcsam
00:00:00 - Intro
00:01:19 - When to use an AI Agent Framework
00:06:05 - Principles for designing Agent Tools
00:11:01 - Human-in-the-loop Architectures
00:17:19 - Working Memory vs Long-term Memory
00:32:03 - The "Lethal Trifecta" of Security Risks
Subscribe for more insights on AI tools, productivity, and AI Agents.
Tool Use is a weekly conversation with the top AI experts.