Model evaluation

The 2025 AI Engineering Report — Barr Yaron, Amplify

The 2025 AI Engineering Report — Barr Yaron, Amplify

Barr Yaon of Amplify Partners presents early findings from the 2025 State of AI Engineering survey, covering LLM usage, customization techniques like RAG and fine-tuning, the state of AI agents, key challenges like evaluation, and community perspectives on the future of AI.

Prompt Engineering for Generative AI • James Phoenix, Mike Taylor & Phil Winder

Prompt Engineering for Generative AI • James Phoenix, Mike Taylor & Phil Winder

Authors James Phoenix and Mike Taylor discuss the evolution of prompt engineering from a creative art to a rigorous engineering discipline. They cover the core principles of prompting, the importance of programmatic evaluation, the role of agents, and how to manage application lifecycles as models evolve.