According to Andrew Ng (@AndrewYNg), the single most important factor influencing the speed of progress in building AI agents is a team's ability to implement disciplined processes for evaluations (evals) and error analysis. Ng emphasizes that while it might be tempting to quickly address surface-level mistakes, a structured approach to measuring system performance and identifying root causes of errors leads to significantly faster, more sustainable progress in developing agentic AI systems. He notes that traditional supervised learning offers standard metrics like accuracy and F1, but generative and agentic AI systems pose new challenges due to a much wider range of possible errors. The recommended best practice is to prototype quickly, manually inspect outputs, and iteratively refine both datasets and evaluation metrics—including using LLMs as judges where appropriate. This approach enables teams to precisely measure improvements and better target development efforts, which is crucial for enterprise AI adoption and scaling. These insights are shared in depth in Module 4 of the Agentic AI course on deeplearning.ai (source: Andrew Ng, deeplearning.ai/the-batch/issue-323/).

According to DeepLearning.AI, the newly launched course 'DSPy: Build and Optimize Agentic Apps' offers a comprehensive introduction to DSPy's signature and module-based programming model, enabling developers to build modular, traceable, and debuggable generative AI agentic applications. The course provides hands-on training for constructing robust AI agents, which is increasingly valuable for enterprises seeking scalable AI solutions. This development highlights a growing trend in the AI industry toward modularity and traceability in generative AI workflows, opening new business opportunities for organizations aiming to deploy and manage complex AI-driven systems efficiently (source: DeepLearning.AI, Twitter, June 6, 2025).