Series · 5 parts
Architecting AI Systems
Practical architecture for LLM systems: rules for using models well, the biases that mislead us, agents versus workflows, and MCP alongside REST.
- 10 Basic Architectural Rules for Effective LLM Use
Ten architectural rules for effective LLM use: system instructions, hard constraints, structured reasoning, examples, context and reusable prompt templates.
- The Ghost in the Code: Navigating the Trap of AI Projection
AI projection and automation bias: why treating language models as collaborators is risky for architects, and how to design transparent, validated AI systems.
- AI Agents vs AI Workflows: What Businesses Need to Know in 2026
The difference between AI agents and AI workflows, when each fits, high-value enterprise use cases and how to build an AI-ready organization.
- Model Context Protocol: The Future of Enterprise AI Integration
What Model Context Protocol (MCP) is, how its host, client and server architecture works, and how enterprises can adopt it securely for AI agents.
- MCP vs REST APIs: When Enterprise Architects Should Use Each
When to use REST APIs, when to use Model Context Protocol, and why most enterprises should layer MCP over existing REST services rather than replace them.