Combine Skills and MCP to Close the Context Gap — Pedro Rodrigues, Supabase
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
Why it matters
If you're building AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → skills or MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → integrations for production databases, this shows why skills and MCP underperform alone but close the reliability gap together — with specific patterns like keeping critical security rules directly in agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → since agents reliably skip reference files.
Key quotes
“I've never spent more time writing a single document since I've wrote my master thesis”
Pedro Rodrigues
“they're very lazy to and very stubborn to admit that they don't know and they do need to find fresh information”
Pedro Rodrigues
“if something can get skipped it will be skipped”
Pedro Rodrigues
“the bottom line is not the the context, it's the guidance”
Pedro Rodrigues
“Be opinionated. You know your product. Don't be afraid to to show it.”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
