Hannah Craighead

Cursor is the first AI-integrated IDE I've used beyond AI auto-complete. Having the LLM chat agent embedded in the IDE is saving me a lot of time. I find it particularly helpful for providing a skeleton of code to edit or for diagnosing source of errors. It's also very helpful for explaining pre-existing code in languages or codebases you are less familiar with

I've been using LangSmith for a couple of months at our startup and it's been incredibly useful for running ongoing LLM evaluations and for evaluating new features. The Python SDK is handy and we've automated LangSmith evals as part of CI/CD on GitHub to spot regressions. My main struggle with LangSmith has been that the UI can be tricky to work with for larger datasets or datasets with a large experiment history. I would also love for the filters to be persisted in the URL. That way I can send a filtered set of failing examples to someone without having to provide instructions for how to reconstruct it.