Overview

Connectors are a fundamental element of the Hunch canvas, representing the flow of information between blocks. These visual links illustrate how data moves through your AI workflow and help establish the dependencies between different components.

Function of connectors

Connectors serve two primary purposes in Hunch:

  1. Data flow visualization: They show how information moves from one block to another, making it easy to understand the structure of your workflow at a glance.

  2. Dependency mapping: Connectors establish which blocks depend on others for their input, helping to determine the execution order of your workflow.

How connectors work

When you connect two blocks, the output of the first block becomes available as input for the second. This allows you to create chains of operations where each step builds upon the results of the previous ones.

Connectors are directional, always flowing from an output to an input. This directionality ensures that data moves through your workflow in a logical and predictable manner.

Importance in workflow design

While simple in concept, connectors play a crucial role in designing effective AI workflows:

  • They encourage modular thinking, breaking complex tasks into discrete steps.
  • They make it easy to reorganize and refine your workflow by visually representing relationships between blocks.
  • They help in troubleshooting by clearly showing the path of data through your canvas.

By thoughtfully using connectors, you can create more organized, efficient, and understandable AI workflows in Hunch.