Connections

A connection wires one block to the next and sets the order they run in. How blocks pass data covers the concept: once a block runs, its output is remembered under the block's name, and any later block reads it by reference. This page is the reference for the connection tag syntax and the output shapes you'll reach into.

Tag syntax

A connection tag references a value from an earlier block's output:

<blockName.path.to.data>

• blockName is the name of the source block. Block names are normalized before matching, so they're lowercased and spaces are removed. <My Agent.content> and <myagent.content> resolve to the same block.
• path.to.data is the path to the value inside that block's output. The field path is case-sensitive.

The same angle-bracket syntax also reads workflow variables (<variable.name>) and loop or parallel context (<loop.index>); a connection tag is specifically the block-output case.

You rarely type a tag by hand. In any input field, type < to open a dropdown of the values available from earlier blocks and pick one, or drag a value from a connected block straight into the field.

Nested and array fields

Chain dot notation to reach into objects, and use bracket indices for arrays. Both combine in a single path:

<agent1.tokens.total>
<api1.data.results[0].id>
<api2.data.users[0].name>

The resolver walks the path at runtime and substitutes the value. Multiple levels of indexing like items[0][1] work too.

Using tags in text and code

Tags resolve at runtime and can sit anywhere in a field, mixed with static text:

// In text
"The user's name is <userBlock.name>"

// In JSON
{
  "userName": "<userBlock.name>",
  "orderTotal": <apiBlock.data.total>
}

// In a Function block
const greeting = `Hello, ${"<userBlock.name>"}!`
const total = <apiBlock.data.total> * 1.1

Values are formatted to fit their context. In a Function block, a resolved value becomes a code literal, so strings are quoted, objects are JSON, and null stays null, ready to drop into JavaScript or Python. In other blocks, objects are JSON-stringified and primitives become plain strings.

When a referenced block didn't run on the current path, for example a block on an unselected branch, its tag resolves to an empty value. In most blocks that's an empty string; in Function blocks it's null.

Common block outputs

A tag's path depends on what the source block produced. These are the standard shapes for the blocks you'll reference most. The output panel shows the live structure for any block.

{
  "content": "The generated text response",
  "model": "claude-sonnet-4-6",
  "tokens": { "input": 120, "output": 85, "total": 205 },
  "toolCalls": []
}

{
  "data": "Response body",
  "status": 200,
  "headers": { "content-type": "application/json" }
}

{
  "result": "Function return value",
  "stdout": "Console output"
}

{
  "conditionResult": true,
  "selectedPath": {
    "blockId": "2acd9007-27e8-4510-a487-73d3b825e7c1",
    "blockType": "agent",
    "blockTitle": "Follow-up Agent"
  },
  "selectedOption": "condition-1"
}

{
  "content": "Routing decision",
  "model": "claude-sonnet-4-6",
  "tokens": { "input": 120, "output": 85, "total": 205 },
  "selectedPath": {
    "blockId": "2acd9007-27e8-4510-a487-73d3b825e7c1",
    "blockType": "agent",
    "blockTitle": "Customer Service Agent"
  }
}

{
  "content": "Evaluation summary",
  "model": "claude-sonnet-4-6",
  "tokens": { "input": 120, "output": 85, "total": 205 },
  "metric1": 8.5,
  "metric2": 7.2
}

A Function's result, an API's data, and an Agent with a response format all return whatever your code, the remote service, or your schema produced, so check the output panel during development to confirm the path you're referencing.

Next