Skip to main content
An Asteroid workflow is a graph. A node is one small task. A transition is a rule that picks what runs next. Together they describe the whole job. You do not write one long prompt. You write several short ones and connect them.

​
Why a graph beats one long prompt

Each step stays small

A node holds one intention, so the model has less to get wrong.

You see where an execution is

An execution reports the node it sits on and the edge it took to get there.

You fix one step

Rewrite one node’s instructions. The rest of the graph stays as it was.

You tune per step

Every node picks its own model and its own capabilities.
One long prompt gives you none of this. It succeeds or fails as a whole. When it fails, you rewrite all of it.

​
The three node types

Nodes

What each node type holds and how you configure it

​
How an execution walks the graph

1

The execution enters the start node

The start node makes no decision. It has one outgoing transition, and the execution follows it.
2

An agent node does the work

The node reads its instructions and acts. It clicks, types, reads pages, and runs scripts.
3

A transition fires

The node has one outgoing transition per possible next step. The workflow picks one, or a selector matches and picks one for it.
4

The next node picks up

The execution moves along the edge. The receiving node sees any data that edge carried.
5

The execution reaches an output node

The output node ends the execution. It returns an outcome label and structured data to your code.
An execution sits on exactly one node at a time. It never runs two nodes at once.

​
One node, one intention

Give a node a single clear job: “Log in”, “Fill driver details”, “Upload documents”, “Read the quote”.
If a node needs more than a paragraph of instructions, split it.
Start with the seeded start node, one agent node, and one output node. Prove the task works, then add structure. Split a node when:
  • The work crosses two portals or two distinct URLs.
  • The work moves between tabs or pages inside one portal.
  • A subtask grows long or gains its own sub-steps.
  • You want a different model or a different timeout for one stage.
Name things for what they mean. The workflow name says what the whole flow does. A node name says what that step does. An outcome label says how the execution finished.

Write good instructions

How to write the instruction block inside a node

​
Every agent node needs a failure path

Connect every agent node to an output node through a failure transition.Without one, a missing element or an unexpected page has nowhere to go. With one, the execution ends on a label you chose, and your code can act on it.

​
What travels between nodes

Each node sees only what it needs. That keeps its context short and its behaviour steady. When data must cross a node boundary, you have two routes.

Transitions

How an execution chooses its next node, and how data crosses an edge

Workflow filesystem

The directories an execution can read and write

​
The graph is not the contract

Your code never names a node. It sends inputs, then reads an outcome label and a result. That contract holds while you reshape the graph behind it.

Inputs and outputs

The contract between a workflow and the code that calls it

Build in the platform

Draw the graph in the visual builder