# Think & Effects | EasyNet Docs

Source: https://easynet.run/docs/aal/thinking

# Think & Effects

Separate model requests from deterministic computation.

think about defines a reasoning request. A configured Host executes the instructions and the kernel validates its result. Here we request an analysis and verdict, then attach a program-defined rubric version.

## Complete example

Save the example as thinking.aal
thinking.aal

```
agent Tutorial is Agent
  public
    ability run(topic: String) -> ThoughtResult effects(think)
      thought = think about topic
        analyze "Identify the central claim in {topic}"
        decide verdict: "Explain whether the evidence supports it"
        derive rubric_version = 1
      return thought
```

[Download .aal](data:text/plain;charset=utf-8,agent%20Tutorial%20is%20Agent%0A%20%20public%0A%20%20%20%20ability%20run(topic%3A%20String)%20-%3E%20ThoughtResult%20effects(think)%0A%20%20%20%20%20%20thought%20%3D%20think%20about%20topic%0A%20%20%20%20%20%20%20%20analyze%20%22Identify%20the%20central%20claim%20in%20%7Btopic%7D%22%0A%20%20%20%20%20%20%20%20decide%20verdict%3A%20%22Explain%20whether%20the%20evidence%20supports%20it%22%0A%20%20%20%20%20%20%20%20derive%20rubric_version%20%3D%201%0A%20%20%20%20%20%20return%20thought%0A)

## Syntax explained

The ability must allow effects(think). Named verb slots such as verdict have type String.

derive rubric_version = 1 is deterministic computation, not a model-generated conclusion.

check and build need no model. Running think requires a configured model Host. A valid result shape does not prove a conclusion true; there is no fixed expected model output.

## Build and run
Terminal

```
cargo run --locked --bin aalc -- check thinking.aal

cargo run --locked --bin aalc -- build thinking.aal -o thinking.aalc
```

You can check and build this example directly. Execution requires a model Host configured using the repository guide.
[Language source and specification](https://github.com/Brain-Cell-Coding/Agent-Assembly-Language/blob/main/docs/native-integration.md)

## Try it yourself

Add a named reasoning slot and run check. Replace effects(think) with effects() and inspect the effect mismatch diagnostic.
[Language source and specification](https://github.com/Brain-Cell-Coding/Agent-Assembly-Language/blob/main/examples/research.aal)