Hi all, here are today's three links:

The importance of Agent Harness in 2026

Phil Schmid discusses why harnesses are important for agents:

An Agent Harness is the infrastructure that wraps around an AI model to manage long-running tasks. It is not the agent itself. It is the software system that governs how the agent operates, ensuring it remains reliable, efficient, and steerable.

Foundation: Introduction to LangChain - Python

LangChain published a new agent course following their 1.0 release:

Learn how to build AI agents with LangChain. Get started quickly using pre-built architectures and model integrations, then debug your agents with LangSmith Observability.

We removed 80% of our agent’s tools

Vercel walks through a simpler agent went from 80% to 100% success.

We realized we were fighting gravity. Constraining the model’s reasoning. Summarizing information that it could read on its own. Building tools to protect it from complexity that it could handle. So we stopped.

If you have any agent-related links you'd like to feature, let me know!

Cheers,
Ivan