Skip to main content

Tasks

Tasks are Python scripts that run on Aisle's infrastructure. You write a Python function, and Aisle handles scheduling, execution, logging, and delivering outputs back to users.

Unlike Workflows — which chain together prompts and scripts in a visual builder — Tasks give you direct code control. Use them when you need loops, conditionals, branching logic, or external API calls that go beyond what a workflow node can express.

What a task looks like​

result = aisle.ai.prompt("Summarize this document", files=[doc])
aisle.create_chat("Your summary", result)

The aisle object is injected automatically. It gives you access to AI models, memories, files, integrations, HTTP, and more — without any import or configuration.

Triggers​

Tasks can be invoked:

  • Manually — from the task editor or via the API
  • On a schedule — cron expressions or plain-language intervals
  • Via webhook — HTTP POST to a generated endpoint
  • From a workflow — as a node in a visual workflow

Outputs​

Tasks can produce two kinds of output:

  • aisle.create_chat() — creates a chat thread visible to a user in the Aisle UI, optionally allowing follow-up replies
  • aisle.output() — sets a structured return value on the execution record, useful when another system is consuming the result

The SDK​

The aisle SDK is available inside every task as a pre-injected object. See SDK Reference for the full API.