Plain English. With diagrams. No jargon.
Concepts that matter, explained for techies who want to actually understand. 90-second primers. 5-minute deep-dives. Searchable glossary.
What is an agent?
Agent vs chatbot vs copilot vs assistant. The words are abused. Here's the real difference.
Read →MCP in 90 seconds
Model Context Protocol explained without the spec jargon. The "why" before the "what".
Read →What "agentic" actually means
The marketing version vs the engineering reality. Hint: it's about loops + tools, not buzzwords.
Read →Tool calling vs function calling vs MCP
Three things people conflate. We disentangle them.
Read →The agentic stack
LLM → memory → tools → orchestration → UI. Visual breakdown of every layer.
Read →RAG in plain English
Retrieval-augmented generation explained without academic notation.
Read →How agentic loops work
ReAct, plan-and-execute, reflexion — the three core patterns.
Read →Context windows: why they matter
Why "1M context" doesn't mean what you think. The lost-in-the-middle problem.
Read →Memory in agents
Short-term, long-term, episodic. What persists, what doesn't, and why it's hard.
Read →Multi-agent systems
When more than one agent is useful. When it's just complexity for its own sake.
Read →Searchable jargon decoder
Every buzzword that gets thrown around — agent, MCP, RAG, tool calling, context, embedding, function calling, prompt injection, system prompt — translated into plain English.
~50 terms at launch, growing weekly as new jargon emerges.
Open glossary