The speaker's primary recommendation for building AI agents is Pydantic AI.
Alternatives mentioned include:
This video provides a comprehensive overview of Cole Medin's AI-first tech stack, detailing the tools and technologies he uses for building software, particularly AI agents. He explains his reasoning for choosing specific tools, offers alternatives, and categorizes them by their application, including core infrastructure, AI agents, RAG agents, web automation, full-stack development, and deployment.
The speaker utilizes PostgreSQL in several ways:
PGVector extension, he uses PostgreSQL as a vector database for RAG agents. While acknowledging that dedicated vector databases might be faster, he prefers PostgreSQL because many RAG strategies also require a regular SQL database to store document or user data.The speaker recommends the following tools for web automation:
For data extraction (pulling documentation ahead of time to store in a knowledge base):
For live web interaction (giving AI agents tools to pull information from the web in real-time):
The key distinction is the timing and purpose of the web interaction:
The speaker outlines several key considerations for deployment and infrastructure:
Deployment Platforms:
GPU Workloads:
Virtual Machines (VMs) / Self-Managed Infrastructure:
Containerization:
CI/CD:
Testing:
AI Code Review: