How Connections Work
Connections are the pathways that allow data to flow between blocks in your workflow. In SteelEngine, connections define how information passes from one block to another, enabling data flow throughout your workflow.
Each connection represents a directed relationship where data flows from a source block's output to a destination block's input.
Creating Connections
Select Source Block: Click on the output port of the block you want to connect from
Draw Connection: Drag to the input port of the destination block
Confirm Connection: Release to create the connection
Connection Flow
The flow of data through connections follows these principles:
- Directional Flow: Data always flows from outputs to inputs
- Execution Order: Blocks execute in order based on their connections
- Data Transformation: Data may be transformed as it passes between blocks
- Conditional Paths: Some blocks (like Router and Condition) can direct flow to different paths
Deleting a connection will immediately stop data flow between the blocks. Make sure this is intended before removing connections.
Connections Inside Parallel Windows
When Maximum active items uses an output reference, connect its source upstream of the window. The reference must identify one unambiguous upstream block; it cannot read a body block, a downstream block, or a workflow variable. See Maximum Active Items for validation and examples.
A Parallel Window can contain sequential Loop blocks, including loops within loops. Connect each loop through its entry and exit; a connection cannot jump into or out of a nested loop's body. Keep each item's connections inside the window, and use the window's output to connect to downstream blocks after all items finish.
JSON Mapper is supported both inside those loops and directly inside the window. Inside a loop, use <loop.currentItem> for the current loop entry and <parallel.currentItem> for the enclosing window item. To reshape the completed loop results, connect JSON Mapper after the loop's exit and read the loop aggregate, such as <rows.results>. Use Object mode when the whole aggregate should be treated as one input rather than mapped entry by entry.
For a JSON Mapper named Summary directly inside the window, set the window's Item result to <summary.result> to collect its output for each item. Blocks inside the window cannot read the window's unfinished results or reach directly into a completed loop's body. Blocks outside the window must read <window.results> (using the window's actual name), rather than referencing Summary directly.
For child workflows, map the current item's values into the Workflow block's inputs. Connect follow-up blocks to that Workflow block and read its returned result, such as <enrich.result>. Keep per-child reporting inside the window so a fast child can report while another child is still running. A block connected after the window waits for the full aggregate.
In Branches mode, assign every direct body block to exactly one named branch. Connect the window's body entry to the start of each branch and keep connections and output references within that branch. A Loop assigned to a branch owns its descendants. Set each Branch result to a block in that branch, outside any nested loop; cross-branch connections and result references fail validation. Results follow branch order and include the stable branchId, even when branches finish in a different order.