> For the complete documentation index, see [llms.txt](https://docs.yagi.fi/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.yagi.fi/developers/automation/how-it-works.md).

# How it Works

{% hint style="info" %}
**Warning**. The protocol is in active development so expect this section to change regularly
{% endhint %}

## Low-level explanation

If you are not familiar with the protocol at the high-level, please read [Yagi Finance Introduction](/yagi-finance-introduction.md)first.

The protocol defines a task interface `ITask.cairo` that consists of two functions:

* `probeTask` – defines conditions for task execution, returns `1` if task is ready to be executed and `0` otherwise
* `executeTask` – executes task.

The task author creates a task contract that conforms to this interface and deploys it to StarkNet. Once deployed, the task smart contract's address is whitelisted by the Yagi team and keepers begin to execute.

Each keeper will first call `probeTask` to see if task is ready for execution and upon receiving a `1` (ready) will invoke `executeTask`. Keepers do this by running dedicated software (see example below).

{% embed url="<https://twitter.com/yagi_fi/status/1485238730319355905>" %}

The task interface model is very flexible and can accomodate several different use cases:

* Regular timed execution (by using `get_block_timestamp()`
* Conditioned execution (by manually checking for certain conditions)
* Deploying a task separately from the contract (by "authorizing" the task to perform certain contract actions).