Human Collaboration Agent
The Human Collaboration agent routes decisions to human reviewers, pausing the workflow until a human provides input. It supports three interaction modes: conversational (free-form chat), standard form (predefined fields), and custom form (builder-defined fields and layout).
This is the primary mechanism for human-in-the-loop (HITL) workflows on the Ema platform.
Use Cases
- A workflow step requires human judgment before proceeding (approvals, quality review, sensitive decisions).
- You need a human to provide additional information that the AI Employee cannot determine on its own.
- Regulatory or policy requirements mandate human oversight for certain actions.
Inputs
| Input | Type | Description |
|---|---|---|
request_message | Text | The message shown to the human reviewer describing what they need to do. |
context | Text | (Optional) Additional context for the reviewer (e.g., the AI-generated draft, extracted data). |
form_fields | JSON | (Custom form mode) Definition of the form fields the reviewer must fill out. |
Outputs
| Output | Type | Description |
|---|---|---|
approved | Boolean | Whether the reviewer approved the request. |
reviewer_response | Text | The reviewer's response text (conversational mode) or form data (form modes). |
The Human Collaboration agent produces two branch edges -- approved and rejected. You must handle both paths in your workflow. Failing to handle the rejected path leaves the user without a response.
Configurations
| Parameter | Description | Default |
|---|---|---|
mode | Interaction mode: conversational, standard_form, or custom_form. | standard_form |
assignees | List of users or groups who can respond to the request. | Workspace default reviewers |
timeout_hours | Hours before the request times out. | 24 |
timeout_action | What happens on timeout: auto_approve, auto_reject, or escalate. | escalate |
instructions | Instructions shown to the reviewer alongside the request. | None |
Interaction Modes
Conversational: The reviewer sees a chat interface and can ask clarifying questions before making a decision. The AI Employee responds to the reviewer's questions using workflow context.
Standard Form: The reviewer fills out a predefined approval form with approve/reject and optional comments.
Custom Form: The builder defines form fields (text, dropdowns, checkboxes, dates) that the reviewer must complete. The form data is returned as structured output.
How to Use This Agent
An email-sending workflow with human approval:
trigger -> knowledge_search -> respond_to_query -> human_collaboration
-> [approved] -> send_email -> workflow_output
-> [rejected] -> fixed_response("Your request was reviewed and declined.") -> workflow_outputRelated Agents
- Response Validator -- for automated validation that can reduce the need for human review.
- Categorizer -- route only sensitive categories to human review.