mcp-and-agent-systems
MCP Is Not the Product, Operating Rules Around It Are
Protocols create possibility. Products are created by boundaries, permissions, evaluation, and task design.
2026-04-23 · makeyourAI.work
Tag
System Design
This tag page stays indexable only because it carries a real descriptive frame and points to substantive posts, not thin archive noise.
mcp-and-agent-systems
Tool Use Without Auth Boundaries Is Just Prompted Overreach
The model should not be trusted simply because the prompt says to behave. Permissions belong to systems, not to wishes.
2026-04-19 · makeyourAI.work
ai-engineering-fundamentals
AI Product Specs Need Failure Modes, Not Just User Stories
A user story tells you what the person wants. An AI product spec must also describe how the system behaves when probability does not cooperate.
2026-04-16 · makeyourAI.work
prompting-and-llm-interfaces
Model Routing Only Helps When the Product Contract Is Stable
Routing between models is useful only after you know what the task is, how quality is measured, and where the real variance comes from.
2026-04-15 · makeyourAI.work
retrieval-and-rag
Context Windows Are a Budget, Not a License to Dump Everything In
A larger context window does not make irrelevant information harmless. It just makes expensive confusion easier to hide.
2026-04-14 · makeyourAI.work
mcp-and-agent-systems
Build Evals Before You Build Agents
An agent without evals is not a system with autonomy. It is a system with excuses.
2026-04-13 · makeyourAI.work
retrieval-and-rag
When RAG Is the Wrong Answer
Many teams reach for RAG because it sounds like the modern answer, not because retrieval is actually the cleanest way to solve the product problem.
2026-04-09 · makeyourAI.work