MMMarco Mornatiinblog.mornati.net·Jun 28 · 17 min readThe AI Orchestrator: Why Intelligent Delegation is the Missing Piece in Your AI Toolchain1. Introduction: The Age of Model Abundance The AI assistant landscape in mid-2026 is one of abundance. According to McKinsey's State of AI report, 78% of organizations now use AI regularly, and the n31B
MMMarco Mornatiinblog.mornati.net·Jun 15 · 16 min readLifting the Lid on Copilot's Black Box: Observability for LLM Code GenerationIntroduction: The Black Box of AI Code Generation When you ask GitHub Copilot to write a function, refactor a module, or explain a complex piece of code, the response you get is the output of a probab10
MMMarco Mornatiinblog.mornati.net·May 31 · 14 min readYour AI Agent Deserves a Tool Harness, Not a Wild WestWe started the same way everyone does: give the LLM access to everything and hope it figures it out. Connect the GitHub MCP, the Jira MCP, the internal product API MCP, throw in a database schema or t00
MMMarco Mornatiinblog.mornati.net·May 5 · 8 min readThe Hidden Tax on Every AI Request: How MCP Servers Are Draining Your Token BudgetLast month, I published a comparison: MCP Servers vs. CLI. Single server (GitHub), controlled test, clear conclusion: Native MCP wastes 99.7% on schema tax in typical sessions. But that's a lab test. 00
MMMarco Mornatiinblog.mornati.net·Apr 27 · 23 min readThe Future of Agentic Tooling: MCP Servers vs. CLI A Data-Driven ComparisonAs Large Language Models (LLMs) evolve into autonomous coding agents, one of the most consequential architectural decisions is deceptively simple: how should an AI agent talk to external services? Tra81S
