Oct 22, 2025

In last week’s letter, I explained how effective agentic AI development needs a disciplined evals and error analysis process, and described an approach to performing evals.

The Batch AI News and Insights: In last week’s letter, I explained how effective agentic AI development needs a disciplined evals and error analysis process, and described an approach to performing evals.

Honing an agent’s prompt can yield better results than fine-tuning the underlying large language model via reinforcement learning.

In the absence of national laws that specifically regulate AI in the United States, California moved to regulate the technology within its own borders, passing four bills in less than a month.

The ability to easily connect large language models to tools and data sources has made Model Context Protocol popular among developers, but it also opens security holes, research shows.

Reasoning models typically learn to undertake a separate process of “thinking” through their output of before they produce final response. Ant Group built a top non-reasoning model that can take similar steps as part of its immediate response.