Beginner
The first reads. Vocabulary, the agent loop, basic workflows, and the failure modes new operators hit.
Start here if you are new to agent systems. These pieces build the vocabulary, the loop, and the basic workflow patterns without assuming prior operating experience.
Concept Briefs
Short explainers on loops, graphs, memory, prompting, and the core vocabulary of agentic systems.
-
From Prompts to Agents: The Gap You're Probably Skipping
Most people who use LLMs daily are running one-shot or multi-turn prompts — not agents. The difference matters more than it sounds. Here is what actually changes when you move from prompts to agents, and why most people discover the gap only after they've built something brittle.
CONCEPTS -
From Prompts to Desks: Why One Agent Is Not Enough
The first time an agent system is set up, it is a single agent in a single session doing everything. That works until it does not. This is the beginner bridge from one generalist agent to a small team of desks with defined roles. What changes, what stays the same, and how to know when the move is worth making.
CONCEPTS -
What Is an LLM?
Large language models are next-token predictors trained on a wide corpus of human-written text. This piece explains what the model actually does, how it is trained, why it hallucinates, and what to look for when choosing one — the technical foundation the rest of the manual presumes.
CONCEPTS -
First Steps: Sessions and Memory
A session is a single conversation. Memory is what survives between sessions. Together they form the agent's lifecycle: each session starts cold, runs hot, and writes something durable for the next one. This piece is a practical first-day explanation of how this works and what the operator actually does.
CONCEPTS -
From Prompts to Agents
A prompt is a one-shot instruction. An agent is a system that runs prompts over time. The move from one to the other is not a single jump — it is a series of additions: system prompt, workspace, tools, memory, loop. This piece is the bridge.
CONCEPTS -
Getting Started with Workspaces
A workspace is the file system plus memory plus agent identity that an agent reads when it wakes up. The shape of that workspace determines what the agent can do, what it knows, and how easy it is to debug when something goes wrong. This piece is a practical first-day guide to what a workspace is, what it should contain, and how to start small and grow deliberately.
CONCEPTS -
Practical Applications: Personal, Team, and Business Agents
Three generations of agent deployments — personal, team, business — differ not in capability but in blast radius, governance, and cost model. This piece is a practical guide to figuring out which generation your use case belongs to, what to build first, and when to graduate to the next one.
CONCEPTS -
What Is AI?
AI is a marketing label that covers several distinct technical generations — rules, classical ML, deep learning, LLMs, agents. The words mean different things at different times. An agent builder should know which generation they are actually using.
CONCEPTS -
Best Ways to Ask an Agent for Things
A good request to an agent has four pieces: role, task, constraints, and examples. The model is roughly as capable as it is going to be — what changes between a working request and a failing one is the prompt that frames the work.
CONCEPTS -
How Does an Agent Think?
An agent thinks in stages: intake, context, inference, tool execution, persistence, termination. Each stage is its own design problem. Understanding the stages is what separates a working agent from one that hallucinates, stalls, or runs forever.
CONCEPTS -
What Is a Graph?
A graph is a collection of nodes (steps) and edges (typed transitions) that an agent moves through. In agent work, graphs are how non-trivial workflows stay auditable, branchable, and reusable. They are not a replacement for loops; they are a structure around them.
CONCEPTS -
What Is a Loop?
A loop is the smallest repeating structure that lets a system make progress on a goal it cannot finish in one pass. In agent work, loops are how an AI system turns a single model call into something that can do multi-step work.
CONCEPTS -
What Is an AI Agent?
An AI agent is a system that takes a goal, gathers context, decides what to do, acts through tools, and keeps working until the goal is done or a stop condition fires. The agent is the loop; the model is one component inside it.
CONCEPTS -
OpenClaw Control on Mac and in the Browser
OpenClaw gives you two surfaces for the same system: a native macOS app and a browser-based Control UI. The Mac app is the local front door. The browser is the workbench. This article explains both, when to use each, and how they fit together.
CONCEPTS -
Pursuing Goal in OpenClaw
Pursuing goal is the feature that gives an OpenClaw session one durable objective, keeps it visible across turns, and turns long-running agent work into something an operator can actually follow. This article walks through what the feature does, why it matters, the six goal states, the goal tools the model can use, the /goal command surface, and the common mistakes a new operator makes.
CONCEPTS -
What Is an Agent Loop?
An agent loop is the repeating cycle an AI agent uses to make progress on a goal. It takes in a request, gathers context, reasons about the next step, uses tools if needed, records what happened, and decides whether to continue or stop. Once the loop is visible, much of agent behavior becomes easier to read, debug, and improve.
CONCEPTS
Workflow Reviews
Pattern reviews: what a given workflow is good for, where it breaks, and how to improve it.
-
Simple Workflows for Beginners
A workflow is a procedure the agent runs on a schedule, on demand, or in response to an event. The simplest workflows are the most reliable. This piece covers what a workflow is, the three trigger shapes, the minimum viable workflow, and the patterns that hold up as you grow.
WORKFLOWS -
Workflow Review: The Daily Triage Routine
A triage routine is the cheapest reliable habit a long-running agent can have. It doesn't replace careful work; it just makes sure the careful work happens to the right thing. The pattern is small enough to ship in a day.
WORKFLOWS