Dive into LangSmith product usage patterns that show how the AI ecosystem and the way people are building LLM apps is evolving.
Another year of building with LLMs is coming to an end — and 2024 didn’t disappoint. With nearly 30k users signing up for LangSmith every month, we’re lucky to have front row seats to what’s happening in the industry.
As we did last year, we want to share some product usage patterns that showcase how the AI ecosystem and practice of building LLM apps are evolving. As folks have traced, evaluated, and iterated their way around LangSmith, we’ve seen a few notable changes. These include the dramatic rise of open-source model adoption and a shift from predominantly retrieval workflows to AI agent applications with multi-step, agentic workflows.
With Large Language Models (LLMs) eating the world, everyone’s asking the mirror-mirror-on-the-wall question: “Which model is the most utilized of them all?” Let’s unpack what we’ve seen.