AgentAI

Microsoft and GitHub recently introduced new usage limits and charges for premium AI models in Copilot. Under the new structure - standard subscriptions now have a strict monthly quota for queries using top-tier models like GPT-4o or Claude 3.5 Sonnet. Once you hit the limit, you either pay extra or fall back to standard base models.

They were completely honest about the reason: the massive operational cost of running advanced frontier models at scale.

Recently, while developing my AI agent library, agentai, I introduced a new CI pipeline to run examples against various models for each pull request. This process ensures that all elements of the library work correctly with each new release. I started by running these tests using GitHub Models, primarily for convenience (as they are already integrated) and to enable external contributors to use the same test suite in the same environment.

Recently, I was working on the AI_Devs course, which aims to teach how AI agents work and how to create them. I completed all the exercises using the Rust programming language, and during that time, I started developing a common library to group code that could be shared across different subprojects for the course. After finishing the entire course, one file — agent.rs — stood out to me as particularly useful in most of the exercises. This was the initial implementation of my library, AgentAI.