AI Agents
Agents are language models that choose their own next step, call tools, and keep going until the job is done. These articles cover how the loop works, how to design tools and memory for it, when several agents help, and how to measure whether an agent is reliable enough to ship.
16 articles tagged AI Agents.
Context engineering: what to put in the window and what to leave out
Prompt wording matters less than what else sits in the context window. Context engineering is the practice of choosing, trimming, and refreshing that content on every model call, and it's where agent quality is won.
Model Context Protocol (MCP) explained for developers
MCP is an open standard that lets AI apps discover and call tools, read resources, and use prompts from any server that speaks it. Here's how it works, when it's worth using, and where the risks are.
How to design tools an LLM can actually use
The quality of an agent's tools sets a ceiling on the agent. Here are the design rules that matter most: fewer tools, clear names, honest descriptions, compact outputs, and errors a model can act on.
Build your first agent with the Claude API in Python
A complete, runnable agent in about fifty lines of Python: two read-only tools, a loop, a step limit, and logging. No framework required, and every line explained.
Tool use explained: how an LLM calls your code
A language model can't run code or hit an API. It can only ask you to. This post explains how tool use works, what the model actually sees, and where things quietly go wrong.
How the agent loop works, step by step
Every agent runs the same loop: send the conversation, get back text or a tool request, run the tool, append the result, repeat. This post walks through one full run and the bugs that trip people up.
What is an AI agent? A plain-English definition
An AI agent is a language model that picks its own next step, uses tools to act, and keeps going until the job is done. Here's what that means, what it doesn't, and when you actually need one.