Replit moved most of its AI spend from Anthropic to OpenAI for a reported 30%+ discount. Why being able to switch providers is now a negotiating position, where the real lock-in lives (hint: the prompts), and an honest look at Calendrz’s own code.
Posts Categorized: AI
Beware of the Markdown File in Your Downloads Folder
A malicious AGENTS.md file in a Downloads folder tricked coding agents into installing a rogue package. Why instruction files are code now, what I’d ask engineering teams to change this week, and how Calendrz treats the emails its own agent reads.
Of Leaders, Workers and Too Many AI Agents
A new Asana report finds leaders use far more AI agents than their teams, while workers lose time juggling them. My take on why the two sides see agents so differently, and why leaders should measure finished work rather than agent activity.
Faster Code, Same Release Date: What Gives?
Engineering leaders say AI agents write code much faster, yet their release cycles are no faster than before. Typing was never the bottleneck: here’s where the time really goes, and what I’d change about review and verification.
Of Banks and AI Agents: Lock the Window, Build a Door
JPMorgan and Schwab are blocking outside AI agents from client accounts. They’re right to, but the interesting part is what Schwab offers instead, and why every CTO should give agents a proper front door (as I did for Calendrz).
LinkedIn Is Retiring Its Search Filters. AI Callers Never Read Them Anyway
LinkedIn is replacing classic filter-based job search with AI search. On the API side of Calendrz, AI clients kept guessing parameter names. Here’s how strict validation plus helpful error messages fixed it.
Your AI Agent Will Book the Meeting. Will It Know When You’re Free?
Meta and Sierra’s Personal Agent Protocol, Google’s Gemini agent and Microsoft’s Work IQ all point the same way: agents will negotiate our time. Here’s why accurate, merged calendar data is the part that decides whether they get it right.
The opposite of AI slop: the agent that reads our production logs every night
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.
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.
