Concept Briefs
Short explainers on loops, graphs, memory, prompting, and the core vocabulary of agentic systems.
Concept Briefs
Short explainers on loops, graphs, memory, prompting, and the core vocabulary of agentic systems.
-
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 -
Cron Jobs, Heartbeats, and Scheduled Work
Cron jobs run an agent session on a schedule. Heartbeats run an agent session at a faster cadence to keep state fresh. The two patterns are how long-lived automation actually gets built — and the design choices around them decide whether the automation is observable or silent.
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 -
Inside the Agent Loop
The agent loop is six stages: intake, context, inference, tool execution, persistence, termination. Each stage is its own design problem. This piece walks through each stage with concrete examples of what can go wrong and how to fix it.
CONCEPTS -
Sessions, Sub-Agents, and Child Sessions
A session is the boundary of one unit of agent work. Sub-agents let a parent session delegate part of the work to a child session. The design choices around session boundaries are what decide whether an agent system scales or stalls.
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 -
Wiki Memory: The Fourth Layer Most Agent Systems Skip
Wiki memory is a hand-edited knowledge base that sits on top of long-term notes and semantic search. It is the fourth layer most agent systems skip — and the layer that keeps a workspace coherent past year one.
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 -
Loops vs Graphs: When to Stop Iterating and Start Routing
Loops are what an agent does to make progress. Graphs are what an operator builds to keep a long-running system out of trouble. Knowing which one you are working on saves weeks.
CONCEPTS -
Memory: Short-Term, Long-Term, and Semantic
Agent memory has roughly three layers: short-term (the current conversation), long-term (notes the agent has saved), and semantic (vectors retrieved by relevance). Each layer has different rules for what goes in and what comes out.
CONCEPTS -
Why memory is the hardest part of any long-running AI workflow
Most operators underestimate the cost of memory until they hit it. A short field guide to the kinds of memory problems that show up after week one.
CONCEPTS