Deploying AI like it's code: A guide to upgrading agents

Опубликовано 28 августа 2025, 20:24

Learn how to deploy and upgrade AI agents using software engineering principles in this episode of Real Terms for AI! Aja and Jason revisit deployment strategies using a pet shop example to explain essential agent architecture concepts. Discover how to upgrade LLMs with traffic splitting and manage database migrations for RAG systems, ensuring seamless integration and peak performance.

Chapters:
0:00 - Introduction
0:26 - Revisiting Deployment Strategies
0:42 - Pet Shop Example: Agent Architecture
2:27 - LLM Upgrades with Traffic Splitting
4:40 - Database Migration for RAG Systems
6:25 - Software Engineering Principles for AI Agents
7:13 - Conclusion

Resources:
Using revisions in Cloud Run for Traffic Splitting, Gradual Rollouts, and Rollbacks → goo.gle/422HYms

Watch more Real Terms for AI → goo.gle/AIwordsExplained
Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech

#AIAgent #DevTips #AI

Speaker: Aja Hammerly, Jason Davenport
Products Mentioned: AI Infrastructure, Gemini