Series
Agent Engineering Notes
Notes on making AI agents work in real systems: protocols, tool layers, context engineering, multi-agent collaboration, safety boundaries, observability, and evaluation.
3 posts · Read in order
- 1
What Is MCP: A Stable Way for Agents to Connect Tools and Context
MCP, short for Model Context Protocol, is an open protocol for connecting AI applications to external systems. It is not about making the model itself smarter. It standardizes how agents access tools, data sources, prompt templates, and business systems.
July 1, 2026 · 6 min read
- 2
What Is A2A: How Different Agents Discover, Communicate, and Collaborate
A2A, short for Agent2Agent, is an open protocol for agent interoperability. It focuses on how agents built by different teams, vendors, and runtimes can discover each other, exchange messages, delegate tasks, and collaborate.
July 1, 2026 · 9 min read
- 3
Agent Skills: Packaging Senior Engineering Discipline Into AI Coding Agents
AI coding agents default to the shortest path: skipping specs, tests, security review, and other practices that make software reliable. Addy Osmani's Agent Skills packages production engineering workflows, quality gates, and best practices into 24 structured skills that agents can consistently follow from idea to launch.
July 11, 2026 · 6 min read