A calmer way to
decode AI language.

A system that uses a model, tools, context, and control logic to pursue a goal and take actions.

AI that plans, uses tools, receives feedback from the environment, and can act with partial autonomy.

The runtime around a model that supplies tools, state, prompts, permissions, logs, and execution loops.

The practice of designing, testing, and simplifying the runtime around an agent so it can work reliably across tools, sessions, and tasks.

Separating the model-and-harness layer that decides what to do from the sandbox, tools, or systems that perform actions.

The repeated cycle where an agent reasons, calls a tool, observes the result, and decides the next step.

A goal that requires many dependent steps, decisions, tool calls, and course corrections before completion.

An agent designed to keep making progress over many sessions, context windows, or wall-clock hours.

An execution mode where a long-running AI task continues asynchronously while the application polls for status or results.

A group of agents that coordinate or compete to solve pieces of a larger goal.

An emerging coding-agent workflow where a persistent objective stays active across progress checks, continuation, pause, and resume.

Saving workflow progress so an agent or graph can pause, fail, or wait for a person and later resume without redoing completed steps.

A deliberate pause inside an agent workflow that waits for external input before continuing.

An architecture where multiple specialized agents collaborate through messages, tools, or a shared controller.

A coordinating agent that decomposes work, invokes specialists, and combines their outputs.

A focused agent invoked by another agent or workflow to handle a narrower task.

A pattern where one agent exposes a specialist agent as a callable tool instead of handing over the whole conversation.

Multiple agent sessions coordinated around shared work, often with peer messaging, task assignment, or separate context.

A controlled transfer of a task or conversation from one agent to another.

A pattern where a central model dynamically breaks work into subtasks and delegates them to worker models.

A workflow where one model produces work and another model evaluates it, creating an improvement loop.

A design where a person reviews, approves, or edits model output before a consequential action happens.

A design where humans monitor autonomous systems and intervene when risk, uncertainty, or policy requires it.

A way to describe how much freedom an agent has to decide, act, spend money, or change systems.