Looking to try a Kaggle competition? I made a kernel to get you started

Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. We built this product to control pre- and post-inference workloads. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. Kastra pushes an allow, hold, and deny decision before the action runs. You can build these policies in plain English from the web app. The interception engine evaluates the tools, targets, and parameters of every action at sub 1ms at a scale of billions of interceptions per day. We also…

Please check it out. I spent all of 2012 learning to code to launch what would eventually become Uncover. I'm super excited to announce that we're finally live. Here's a blog post I wrote on how we got there and a little story behind the startup: http://spencerfry.com/introducing-uncover

Turn your datasets into prediction engines

5/6 · The workflow of a professional quant trading firm.

Give LLMs rich context about Kaggle competitions

Share, collaborate on, and analyze open data