Analysis

LLM Evaluations

In the fast-evolving AI applications, language model evaluations — or “evals” — have become essential for businesses leveraging LLMs in their products.

Optimizing Schema Properties for LLM Inference

When working with large language models (LLMs), one of the most overlooked factors impacting the quality of LLM inference is how schema properties—the names and descriptions of fields in your data—are defined.

Chat Prompts Are Not Enough

As we get into practical AI-assisted workflows, it’s clear that simply prompting an agent to fulfill your goal isn’t enough.

AI / User Collaboration Paradigms

OpenAI’s new language models, o1 and o1-mini, mark a significant shift in AI development.

AI and Future of Work

As AI and large language models (LLMs) become more integrated into business workflows, the roles of knowledge workers will shift.

RAG: Build or Buy

Sometimes I’m being asked whether it’s better to buy a commercial solution for RAG or build something using … (enter your preferred tech LlamaIndex, Langchain, etc.