-
In short When building AI applications with large language models (LLMs), prompts play a crucial role in the quality of the application’s output. A bad prompt can lead to poor results even with the best models. On the other hand, a well-crafted prompt can perform badly if the underlying model is not suitable for the…
-
In short With many users and companies building agents a new challenge arises: interoperability. How can agents communicate with each other when they are built on different platforms and frameworks? Google announced the Agent2Agent (A2A) protocol a few months ago to tackle this issue. In this article, I want to explain why a protocol is…
-
In short The OpenAI Agents SDK is an open-source, lightweight Python SDK that can be used to build agentic applications. The SDK was launched March this year (2025) and the successor to OpenAI’s earlier initiative, Swarm, which has been deprecated. It’s an easy-to-understand SDK without too many abstractions. The problem with many agent frameworks and…
-
In short Most language models (LLMs) have a knowledge cutoff of a few months ago and by default they can’t communicate with external systems. This means they can’t search the web, access documents, browse your file system, or read/send emails. Function calling provides the solution, allowing LLMs to (indirectly) connect with these external systems and…