Ai
61 posts
Sentinel: Using MCP Sampling to Analyze Your Own Tool Security
Building an MCP server that uses sampling to discover your connected tools and analyze them for security risks, with no API keys required.
MCP Sampling and Elicitation: The Features That Make Servers Smart
A technical guide to MCP sampling and elicitation: two powerful features that let MCP servers talk back to the client's LLM and ask users for input.
How I Use AI to Act on Ideas, Not Just Collect Them
Two changes doubled my follow-through on ideas: defining a first step for everything, and building a bridge to AI tools for execution.
Team MCP Servers - From Personal Tools to Shared Infrastructure
The case for hosting your MCP servers instead of running them locally, and why the difference matters more than you'd think for teams.
AI Regulation One Year Later: What Changed in 2025
A year after our global AI regulation series, we revisit every jurisdiction to cover new laws, enforcement milestones, and shifting political dynamics.
python-skills: Packaging Library Development as Claude Skills
I turned my Python library development guide into a set of independently installable Claude skills. Here's what they are and how skill marketplaces work.
Training a Deep Q-Network for Trading
How we're using Deep Q-Networks to learn trading decisions, and the techniques that make training stable enough to actually work.
Reviving Graduate School MATLAB with Claude Code
How I used AI coding assistants to transform decade-old MATLAB research code into a modern Rust library with Python bindings. The origin story of ParGA.
How I Write Software With AI
My workflow for building data-intensive services has gotten messier and faster. AI tools have made throwaway code cheap, which changes everything.
Evergreen Gets Even Evergreener
Continued development of my personal CRM Evergreen and how AI agentic coding with Claude and MCP helps make rapid iteration happen.