Blog
Notes on agents at work.
Practical guides on MCP, AI agents and seeing what they’ve done without reading the chat log.
Explainers5 min read
MCP vs API: When to Use Each (and Why You Might Use Both)
Compare MCP vs API with a daily reporting example. Learn when to call an API directly, when to expose an MCP tool, and when to use both.
ReadGuides7 min read
Cursor MCP: How to Add an MCP Server to Cursor (Local and Remote, 2026)
Cursor MCP setup in plain steps: add local or remote MCP servers with mcp.json or Customize, sign in with OAuth, approve tool calls and fix silent failures.
ReadGuides9 min read
Human in the Loop AI: What It Means and How to Approve Agent Actions From Your Phone
Human in the loop AI explained: where people fit in an AI system, how it differs from human on the loop, and how to approve agent actions from your phone.
ReadGuides15 min read
AI Agent Dashboard App for iPhone: A Buyer's Guide to Session vs Results Tools
Choosing an AI agent dashboard app for iPhone? Learn the difference between session tools and results dashboards, what to look for, and a checklist.
ReadGuides17 min read
How to Add a Custom Connector in Claude (Apps and Claude Code)
Add a remote MCP server to Claude as a custom connector, sign in with OAuth, and check it worked, in the Claude apps and in Claude Code.
ReadGuides15 min read
How to Build a Live Dashboard with Claude: 3 Options Compared
Three realistic ways to build a live dashboard with Claude: artifacts, a Claude Code web app you host, or an MCP tool that renders it. Trade-offs included.
ReadGuides15 min read
Human-in-the-Loop AI Agent Approval: What Needs Your Yes
Which agent actions should wait for your approval, how to design the approval step, and how to approve from your phone without writing framework code.
ReadExplainers15 min read
What Is a Remote MCP Server? A Plain-English Guide for Founders and Operators
What is a remote MCP server? Why one URL and one OAuth sign-in replaced config files and pasted API keys, and what it changes for your agent.
Read