While LinkedIn fights AI slop, an AI agent has quietly opened 42 merged fix PRs at Calendrz by reading production logs at 3 a.m. Here’s how it avoids producing slop of its own.
AI agents are joining your meetings. Do they know when you’re actually free?
Agents are moving into meetings and calendars. Here’s what six months of running an MCP server and a scheduling agent taught me about letting AI book your time.
The return-to-office fight is really a calendar problem
Three-day mandates, four-day weeks, deferred rollouts: whichever policy wins, it plays out in a calendar that rarely tells the truth about when you’re free.
AI Agent Permissions: Lessons From OpenAI’s Canceled GPT-6.1
OpenAI cancelled GPT-6.1 Astra because it acted without permission and misreported what it did. Here’s how the Calendrz MCP server handles scope authorization — and a checklist for anyone giving an LLM tools that change state.
Bootstrapping All the Way Up: Build the System That Builds the System
The C compiler compiled itself. We have been bootstrapping for fifty years. AI just gave the loop a fast enough clock that building the system that builds the system finally compounds inside a single career.
Stop Building Systems. Build the System That Builds Them.
We have always measured engineering orgs by what they ship. That was a proxy. The real asset is the loop that produces it — and AI just changed its clock speed.
Ideas Were Never Cheap. Execution Just Got Free.
For most of a founder’s career, the most expensive thing they owned wasn’t money — it was patience. AI just refunded the tax, and that inverts the oldest cliche in startups.
20 Years of liviutudor.com: From ‘New Error’ to AI Era
Twenty years ago, a blank WordPress editor blinked at me. I typed something about “the dawn of a new era” and then immediately bracketed it with a joke: “(or maybe I should spell it as ‘the dawn of a new error’ ?)”. I had no idea how prophetic that would turn out to be. Not […]
Agents, MCP, and what a 19-hour build changed about how I think
The Calendrz Smart Scheduler went from first commit to default-enabled in production in 19 hours. Here’s the architecture — manual agent loop, 13 scheduler tools mirroring 30 MCP tools, prompt caching on two breakpoints — and the meta-story about AI-assisted coding compressing what used to be a sprint into a day.
Voice + MCP: The Interface That Finally Kills the Dashboard
In my previous post, I argued that UIs are becoming optional: that MCP turns your AI assistant into an IDE where every product is just a plugin. But that post still assumed you’re sitting at a keyboard, typing prompts into a chat window. Take the keyboard away. Now what? Voice changes the equation entirely. MCP […]
