Brand Kit Variables

Expose Brand Kit fields (text, lists, personas, color palette) as connectable workflow inputs

What does this node do?#

The Brand Kit Variables node turns fields from the active Brand Kit (brand name, tone of voice, color palette, personas, content pillars, etc.) into structured workflow inputs you can wire to any downstream node. One node holds many variables — each configured variable exposes its own output port.

Common uses:

• Inject a Persona into an LLM prompt without hardcoding it
• Let the user choose which persona or industry to target when launching the workflow
• Drive image generation with the brand’s color palette
• Pass brand.logo as its CDN/GCS image URL to dashboard or email workflow nodes
• Reuse one workflow across multiple brands by switching the active Brand Kit

Canvas configuration#

Variables are stored on the node as an ordered list. The settings panel lets you:

• Add a variable with the ”+ Add variable” button at the bottom (new rows don’t push the list off-screen)
• Pick a variable type from a sectioned dropdown (mirrors the Brand Kit detail page sections)
• Toggle Multiple on list types (Persona, Industry, Values, etc.)
• Preview the output shape via the What this variable contains accordion
• Remove a variable with the trash icon — its port disappears from the canvas

The list is saved on the node. Each change updates the ports immediately.

Required workflow settings#

The workflow must have a default Brand Kit (gear icon → Brand Kit section). Without an active Brand Kit:

• a banner on the canvas flags the issue;
• the Run button in the launch form stays disabled.

Brand Kit administration#

The node reads values from a Brand Kit maintained in the admin area — not from text you type on the node. Create and complete your kits (Business, Audience, Style & voice, etc.) before exposing variables on the canvas.

See Brand Kit for access, creation, and section details. For workflow-level activation and the {{brand.name}}, {{brand.toneOfVoice}}, … syntax in text fields, see Using variables — BrandKit.

Quick setup#

Configuration parameters#

Per-variable settings (canvas)#

Variable types#

Each Brand Kit field shows an output type in the menu (on the right). That type tells you what the port emits at execution time — text, object, or array.

Business#

Examples: Brand Name (String), About the Brand (Long string), Logo (Image URL). Unique values — read from the Brand Kit, no selection at launch.

Brand identity#

Mission or Core Beliefs → single text. Industry, Values → lists: the Multiple toggle controls whether the user picks one or several values at launch.

Audience#

Persona (Object list) is the most common case for the Multiple toggle. Gender (String) stays a single value.

Style & voice#

Tone of Voice, Writing Rules → long text, direct output. Guardrails → list, with Multiple if needed.

At launch: do you need to pick a value?#

Variable type	When launching the workflow
Text, URL, or single object (Brand Name, Tone of Voice, Color Palette)	Read-only preview — no selection
List, Multiple off (e.g. one Persona)	Dropdown — pick one value
List, Multiple on	Multiple choices, or Use all to include every item in the Brand Kit

Persona: one or many outputs?#

Multiple off — one persona#

The user picks one persona in the launch form. The output is an object:

{
  "id": "6a76b519-5d8e-47cc-bc6e-1907bc808967",
  "name": "Sarah",
  "description": "Marketing Manager",
  "demographics": { "age": "28", "location": "Paris" }
}

In an LLM prompt: {{BrandKit_Variables_0.Persona.name}} → Sarah

Multiple on — several personas#

On the canvas, enable Multiple: the type becomes Object list and the port is named Persona (Multi).

When launching the workflow, the Inputs form shows the configured variables. Pick the Brand Kit first, then set each list field:

Use all enabled (default behaviour)#

Use all is on: every persona in the Brand Kit is included automatically. No manual selection needed. The output is a JSON array with each persona in the kit.

Manual persona selection#

Turn Use all off to pick personas yourself. Here, Sarah and François are selected — only they appear in the output JSON array.

Example output with Sarah and François selected:

[
  {
    "id": "6a76b519-5d8e-47cc-bc6e-1907bc808967",
    "name": "Sarah",
    "description": "Marketing Manager",
    "demographics": { "age": "28", "location": "Paris" }
  },
  {
    "id": "a39d17af-0acf-4910-9b70-deeb895fb5ab",
    "name": "François",
    "description": "Digital Performance Manager",
    "demographics": { "age": "48", "location": "Paris" }
  }
]

Process each persona: wire the port to a Loop node to run the next steps once per persona. You can also add a JSON Path Extractor on the array to target a specific field:

JSON Path	Result
$[0]	Sarah’s full object
$[0].name	Sarah
$[1].name	François
$[1].demographics.age	48

Another example — Industry (Multiple on):

["Sportswear", "Footwear"]

JSON Path: $[0] → Sportswear, $[1] → Footwear

Usage examples#

One persona in an LLM prompt#

The user picks Sarah at launch. The LLM receives {{BrandKit_Variables_0.Persona.name}} and {{BrandKit_Variables_0.Persona.description}} directly.

graph LR
    A[Brand Kit Variables: Persona] --> B[LLM]
    A2[Short Text: Topic] --> B

Several personas with a loop#

Multiple on + Use all (or manual selection). The Persona (Multi) port feeds a Loop; each iteration handles one persona.

graph LR
    A[Brand Kit Variables: Persona Multi] --> B[Loop]
    B --> C[LLM: message per persona]

Inside the Loop, reference the current persona or use a JSON Path Extractor ($.name, $.description, …).

Brand colour for Text to Image#

graph LR
    A[Brand Kit Variables: Color Palette] --> B[JSON Path Extractor: $.primary]
    B --> C[Text to Image]

Best practices#

• One variable = one port. Need both Persona and Brand Name? Add two variables on the same node.
• Multiple off when the downstream node expects a single value (LLM prompt, Conditional).
• Multiple on + Loop to process several personas or industries one at a time.
• JSON Path Extractor whenever the output is an array or nested object (palette, multiple personas).
• Use all if you want to cover every Brand Kit item automatically without updating the workflow.

Common issues#

The user sees raw translation keys instead of labels

Cause: Stale cache in the development environment.

Solution: Reload the page (Cmd+Shift+R) or restart the dev server.

The Run button is disabled

Cause: No default Brand Kit is set in the workflow settings.

Solution: Open settings (gear icon) → Brand Kit section → pick an active kit.

A list shows no options at launch

Cause: The Brand Kit has no items for that field (e.g. no Personas).

Solution: Complete the Brand Kit in the admin area, then launch the workflow again.

Empty multi-select rejected

Cause: Multiple is on, Use all is off, and nothing is checked.

Solution: Check at least one item, or enable Use all.

A chosen persona has disappeared

Cause: It was removed from the Brand Kit between configuration and launch.

Solution: Launch the workflow again and pick a persona still present in the Brand Kit.

Related nodes#