Patterns
9 articlesRecurring architectures in AI systems.
What are AI benchmarks?
A benchmark is a standardized test that measures a model's ability on a specific task and lets you compare models against each other.
What is the Guardrails Pattern in AI?
Guardrails are validation layers that control what goes in and out of an LLM to prevent harmful, off-topic, or poorly formatted responses.
What Is Spec-Driven Development (SDD)?
SDD is a discipline where every phase of AI-assisted development leaves a formal artifact before code gets written, instead of improvising as you go.
Edge Cases Discovered With AI
Asking AI to propose the edge cases you didn't think of is a genuinely generative use: it surfaces what you didn't know was missing.
DESIGN.md: The Contract Between Design and Code
DESIGN.md documents your design system in text so an AI agent like Claude Code can inherit and implement it without reinventing decisions.
LLM Evaluation: How to Measure Response Quality
LLM evaluation systematically measures response quality using automated metrics, LLM-as-judge, benchmarks, and human validation.
What is Function Calling in LLMs?
Function calling lets an LLM request the execution of external functions — APIs, databases, computation — and use the result to answer with live, accurate data.
How to Automate Tasks With Make or Zapier Using AI
Make and Zapier now offer LLMs as native building blocks. Learn to build automations that read, classify, and generate content with AI — no code required.
What is RAG (Retrieval-Augmented Generation)?
RAG combines information retrieval with text generation to deliver accurate answers grounded in your own data.