Skip to main content
AmigoFish

Code with Cosmos: Operating AI Agents in Production

From Microsoft Developer · · 7 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.

If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.

Watch on YouTube

Not rated yet

Description

How do you take an AI agent from a working demo to a production-ready system? Marko Hotti and Madeline Egan walk through a practical framework to observe, evaluate, and optimize AI agents with Azure Cosmos DB. Explore the full repo: https://aka.ms/cosmos-travel-planner Watch the full series: https://aka.ms/CodeWithCosmosPlaylist

Learn how traces, evaluation suites, regression testing, and before-and-after metrics can help improve retrieval, latency, token usage, memory efficiency, and Azure Cosmos DB request unit consumption across the data, retrieval, memory, and LLM layers.

💻 GitHub repo: https://aka.ms/cosmos-travel-planner ▶️ Watch the full series: https://aka.ms/CodeWithCosmosPlaylist Try Azure Cosmos DB for free: https://aka.ms/trycosmosfree

Back to Microsoft Developer · Report a problem