A collection of 11 posts
Seven AI agents for work compared on context, control, reach and cost: ChatGPT, Claude, Vibe Dot, Microsoft Copilot, the Gemini agent, Zapier and Lindy.
A Stacklok survey of 520 leaders found 8% use one model provider, and MCP integrations (53%) and multi-step workflows (52%) are hardest to migrate. Here's how to vet agent developers on portability, MCP security, evals, sandboxing and cost, with a scorecard and paid work trial.
OpenAI dots are always-on ChatGPT agents on GPT-6 Astra, each with its own cloud computer and 4,000+ app plugins. Who gets them, what they cost, setup, safety rules, limits, and how they compare with Meta Muse and Grok Bot.
Grok Bot is SpaceXAI's always-on agent on its own cloud computer. What it costs on Cursor and SuperGrok plans, which model runs it, Enterprise, Plaid finance, Team Bots, the dot.com redirect, Voice Transcribe 2.0, and what's confirmed about Grok 4.8 and Grok 5.
Meta Muse is Meta's personal AI agent app, launched 8 Sept 2026 on Muse Spark 1.3. What it does, how the Secure VM and Sentinel work, pricing, Muse for Mac, Muse Connectors, privacy, and how it compares with Claude Cowork and Gemini Spark.
MCP's real attack surface in 2026 - prompt injection, tool poisoning, token passthrough, confused deputy, SSRF - and how to harden a server with OAuth 2.1, scoping, input validation, and human-in-the-loop.
A practical, end-to-end guide to building an MCP server in Python: scaffold with the official SDK, expose tools, resources, and prompts, run over stdio and Streamable HTTP, debug with the Inspector, and register in Claude Code and Cursor.
The 13 best AI task managers in 2026, split into three tiers — AI-enhanced team tools (Linear, Notion, ClickUp), AI personal time-blockers (Motion, Reclaim, Sunsama), and AI agent orchestration boards (Codersera, Vercel Sandbox, Devin). Picks, prices, and a decision matrix.
In a single month, xAI shipped a coding agent, a skills system, and a connectors layer. Here's how Grok Build 0.1, Grok Skills, and Platform Connectors fit together — and how the stack compares to Claude Code, Cursor, and Copilot Workspaces.
Mistral Medium 3.5 is a 128B dense model with built-in reasoning, coding, and agentic capabilities. Le Chat Work Mode turns it into a multi-tool agent. Here's what's new, what it costs, and when to actually pick Mistral over Claude or GPT.
Manus AI in May 2026: the Meta $2B acquisition was blocked by China's state planner on April 27, the Desktop app's My Computer feature puts the agent on your local machine, and pricing, access, and the autonomous-agent landscape sit where they sit.