agents

/goal

Type /goal and describe what done looks like. Claude Code or Codex then keeps working and checks itself until it's finished, even overnight.

/loop

/loop hands an agent a repeating job. It works in rounds, prompting itself each tick, until the work is finished or you stop it.

Agents

An AI agent takes a goal, picks its own tools, does the work, and checks the result. What that means in practice, and where agents are used today.

Claude

Claude is Anthropic's family of AI models, reached through the Claude apps, the API, or Claude Code. What it is known for and how people use it.

Context engineering

Context engineering is deciding what a model sees on each call. Why long chats get worse, and the habits that keep an agent sharp.

Critique loop

A critique loop has one model do the work and a second model review it before you accept it. A simple way to raise quality without more prompting.

Harness

A harness is everything wrapped around a model that turns it into a working [agent](/ai-field-guide/agents). Tools, memory, workspace, the loop that keeps it running.

Hermes

Hermes is a family of open-weight models from Nous Research, fine-tuned from open bases like Llama to follow instructions closely.

Karpathy coding guidelines

Coding guidelines drawn from Andrej Karpathy's take on where AI agents go wrong. Think first, keep it minimal, make surgical edits.

Kimi

Kimi is Moonshot AI's open-weight model family, built for agent work and competing with the closed frontier on coding and reasoning.

Local vs cloud AI

AI in the browser runs in the cloud, outside your computer's trust boundary. Desktop AI tools are installed locally, so they can reach your files.

MCP

MCP is a standard way to plug an AI into your tools and data, replacing a custom connector per service with one shared protocol.

OpenClaw

OpenClaw is an open-source personal agent that runs on your own machine. Message it from WhatsApp or Telegram and it carries out real tasks.

Personal Agent Protocol (Poppy)

Personal Agent Protocol (Poppy) is a draft standard for how your AI agent signs in and acts with a company for you, and how it relates to MCP.

Prompt injection

Prompt injection hides instructions inside text an AI reads, and the model follows them as if they came from you. Why it works, and how to limit it.

Remotion

Remotion renders real MP4 videos from React code, so a coding agent can build an animated video from a plain description.

Skills

A skill is a folder that teaches an agent to do one task your way, every time. What goes in a SKILL.md, and how to keep a library of skills useful.