Agents
10 articlesSystems that reason, use tools and act.
What is an AI agent?
An AI agent is a system where the language model itself decides what steps to take, in a loop, to reach a goal.
What Are Agent Hooks?
A hook is a command the environment runs whenever an agent lifecycle event fires, without going through the model's judgment.
What Is Harness Engineering?
Harness engineering is designing the full environment around an AI agent — rules, memory, skills, orchestration — so it works consistently, not just intelligently.
Human-in-the-Loop (HITL): Integrating Human Oversight in Agents
HITL is a design pattern where a human reviews, approves, or corrects agent decisions before critical actions are executed, balancing autonomy with control.
What is a Self-Reflection Agent?
A self-reflection agent evaluates its own output, detects errors, and corrects itself before delivering a final response to the user.
How to Create Your Own Custom GPT
Custom GPTs are tailored versions of ChatGPT with your own instructions, knowledge, and actions. Learn to build one without writing code.
How Do AI Agents Communicate With Each Other?
AI agents communicate through structured messages, async queues, and coordination protocols. Learn the key patterns to build multi-agent systems.
AI Agent Skills
Skills are modular capabilities that an AI agent can invoke to interact with external systems and data.
What is the Model Context Protocol (MCP)?
MCP is an open standard that connects AI models to external tools and data sources through a universal protocol.
What are AI Coding Agents?
AI Coding Agents are AI assistants that read, understand, and modify code in an existing project, going beyond autocomplete.