Get Started using AI for Process

​

Prerequisites

• Kore.ai account with AI for Process access.
• Admin permissions for initial setup.
• (Optional) API credentials for external integrations.

​

Access AI for Process

1. Navigate to the Platform.
2. Select AI for Process from the product menu.
3. Choose or create a workspace.

​

Workspace Setup

​

Create a Workspace

1. Navigate to Administration → Workspaces.
2. Click Create Workspace.
3. Configure:
   • Name and description.
   • Default model settings.
   • Team access.

​

Invite Team Members

1. Go to User Management.
2. Click Invite Users.
3. Assign roles:
   • Admin — Full workspace access.
   • Developer — Create and edit workflows.
   • Reviewer — Process Inbox tasks.
   • Viewer — Read-only access.

​

Quick Starts

​

Build a workflow

1. Navigate to Workflows.
2. Click Create Workflow.
3. Enter workflow details:
   • Name: “Document Summarizer”
   • Description: “Summarizes uploaded documents”

[Start] → [Text-to-Text AI] → [End]

1. Start Node — Already present, configures trigger.
2. Text-to-Text AI Node — Add from AI Nodes palette.
3. End Node — Add to complete the workflow.

Node: Summarize Document
Type: text-to-text
Model: gpt-4
Prompt: |
  Summarize the following document in 3-5 bullet points:

  {{input.document_text}}

  Focus on key findings and action items.
Output variable: summary

1. Click Test to run with sample input.
2. Review output and logs.
3. Click Deploy to make available.
4. Copy API endpoint for integration.

​

Add human review

[Start] → [Text-to-Text AI] → [Human Review] → [End]

1. Add Human Node after AI node.
2. Configure review settings:

Human Node: Review Summary
Task type: approval
Assignees:
  - role: reviewer
Instructions: |
  Review the AI-generated summary.
  Approve if accurate, or edit and approve.
Fields:
  - name: summary
    type: text
    editable: true
  - name: approved
    type: boolean
Timeout: 24h

1. Navigate to Inbox.
2. View pending review tasks.
3. Review AI output.
4. Approve, edit, or reject.
5. Workflow continues after action.

​

Configure the Model Hub

1. Navigate to Models → Model Hub.
2. View available models:
   • Open-source — Hugging Face models.
   • External — OpenAI, Anthropic, Google.
   • Fine-tuned — Your custom models.

1. Go to External Models.
2. Click Add Provider.
3. Configure credentials:

Provider: OpenAI
API Key: sk-...
Models:
  - gpt-4
  - gpt-4o
  - gpt-3.5-turbo

AI Node Configuration:
  model_source: external
  provider: openai
  model: gpt-4
  temperature: 0.7
  max_tokens: 500

​

Next Steps