Research Signal

Task type: Research Signal

Use Research Signal to research and score a specific propensity signal, producing both evidence and a score.

Run behavior

• Side effects: This task is read-only or computation-only by default. It returns data for later steps rather than directly writing records or sending messages.
• Credit usage: This task can consume organization credits or model/research capacity depending on your plan and configuration.

When to use this task

• Evaluate whether an account matches a buying signal.
• Score a market event or business condition against your ICP.
• Write signal reasoning back to account or opportunity fields.

Setup tips

• Define the signal name, key, and description clearly.
• Keep the signal narrow enough to score consistently.
• Use downstream Update Record tasks to store score and reasoning.

Examples

Hiring signal

Research whether an account is hiring RevOps or SalesOps roles and score how strongly that indicates buying intent.

Outputs

• Signal research, score, and reasoning.

Common pitfalls

• Creating broad signals that cannot be scored consistently.
• Mixing multiple independent signals in one task.
• Ignoring low-confidence or missing-evidence cases.

Reference details

These details are generated from the workflow task registry and match the fields available in the builder.

Required fields

• signalName
• signalKey
• signalDescription

Variable-aware fields

Fields that accept variable references ({{ inputs.x }}, {{ steps.N.y }}) from the workflow's variable graph:

• signalDescription
• researchMessages
• scoringMessages
• researchPrompt
• alignmentPrompt

Liquid template fields

Fields that are rendered through Liquid (variables plus filters and control flow):

• signalDescription
• researchMessages
• scoringMessages
• researchPrompt
• alignmentPrompt

Builder guidance

When the Workflow Builder Genie configures this task, it follows this guidance:

Use when the desired output is a scored research signal with reasoning.

Default configuration

New instances of this task start with the following configuration:

{
  "name": "Research Signal",
  "outputKey": "research_signal",
  "taskType": "Research Signal",
  "description": "",
  "signalName": "",
  "signalKey": "",
  "signalDescription": "",
  "researchMessages": [],
  "scoringMessages": []
}