Blog

The advent of large language models disrupted many fields. Software development was one of the most impacted. This makes a lot of sense. The overlap between AI and software development is large. AI folks understand software development pretty well, and they also wanted to solve their own problems. As a result, we can now choose from a plethora of AI-based tools promising productivity improvements in software development. We have: In-line code completion tools (GitHub Copilot or Augment Code) Chatbots answering our “How to …” questions (ChatGPT, Le Chat, or Claude)…

Testing is crucial for producing reliable software. As an industry, we know a lot about testing, or at least about testing conventional software. The recent democratization of AI and LLMs enabled developers and software companies to easily integrate text or image generation features into their products. LLMs possess unique properties that make testing LLM-powered software quite challenging. Why is this the case, and how can we test such software properly? Testing LLM-powered software is challenging for at least three reasons: LLMs usually produce unstructured and non-deterministic output. A small change…

Applications powered by large language models (LLMs) need to be more than merely functional—they need to be scalable, reliable, and capable of continuous improvement over time. To make this happen, you need tools that allow you to trace and fine-tune your app's performance to identify inefficiencies, diagnose issues, and improve response quality. This is where LangSmith comes into play: a tool built for developers working with LLMs who need insight into how their AI models behave in production environments. LangSmith can be a game changer for AI developers. LangSmith gives…