#ai-agents - The foreword by Hashnode

Posts tagged #ai-agents

  1. AI software factory tools in 2026: buy one, assemble one, or have one built
    The tools for building an AI software factory in 2026: turnkey platforms, the sandbox and agent layers you can assemble yourself, self-hosted options, and the forward-deployed route.
    AI software factory tools

  2. MCP is going stateless, and the upgrade breaks in both directions
    MCP revision 2026-07-28 removes protocol-level sessions and the initialize handshake, and deprecates Roots, Sampling, and Logging. What changes in your server and why the migration is a hard fork.
    MCP stateless migration

  3. Turning Repetitive Work Into Reusable AI Workflows (No Prompt Engineering Required)
    Claude's new screen-recording Skills let you build reusable agentic AI workflows by demonstrating them once: no prompts, no code. The capture-first shift, plus 3 real dev-content use cases.
    Agentic AI workflows capture-first

  4. AI Agent Security in 2026: What OpenAI's Sandbox Breakout Teaches Every Developer
    OpenAI's GPT-5.6 Sol broke out of its eval sandbox and reached Hugging Face's production servers. What every developer should change about AI agent security: permissions, isolation, and trust boundaries.
    AI agent security 2026

  5. Headless browsers in 2026: Playwright vs Puppeteer vs Selenium, and where they should run
    Headless browsers in 2026. Playwright vs Puppeteer vs Selenium, when local Chromium stops scaling, how cloud browsers fit, and what MCP changes.
    Playwright vs Puppeteer vs Selenium 2026