Relay Workflow Integration - AgentFlow Documentation

Overview

Integrate Relay workflows with AgentFlow to automate business processes with AI-powered decision making. Relay combines workflow automation with human-in-the-loop approvals and AI assistance.

Prerequisites

Relay Account

API Access

Generate API key from Relay settings

Workflow Created

Build workflow with API trigger

AgentFlow Admin

Admin access required

Step 1: Setup Relay Workflow

Create New Workflow

Log in to Relay.app
Click Create Workflow
Name: AgentFlow Automation
Description: Process requests from AgentFlow chat

Add API Trigger

Select Trigger Type

Click Add Trigger
Choose API / Webhook
Select When API call is received

Configure Trigger

Method: POST
Authentication: API Key
Click Generate API Key
Copy the API key and webhook URL

Define Input Schema

{
  "message": "string",
  "user_id": "string",
  "timestamp": "string",
  "context": "object"
}

Build Workflow Logic

Add steps to process the request:

Parse Input

Set Variables step:

message = {{trigger.message}}
user_id = {{trigger.user_id}}
timestamp = {{trigger.timestamp}}

AI Processing

AI Assist step:

Prompt: “Analyze this message: ”
Model: GPT-4
Output: analysis_result

Conditional Logic

Condition step:

If analysis_result.priority === "high"
  → Route to urgent path
Else
  → Route to standard path

Execute Actions

Update database
Send notifications
Call external APIs
Log to systems

Return Response

API Response step:

{
  "data": {
    "execution_result": "{{workflow.output}}",
    "status": "success",
    "workflow_id": "{{workflow.id}}"
  }
}

Publish Workflow

Click Test Workflow with sample data
Verify all steps execute correctly
Click Publish
Note the workflow ID and API endpoint

Step 2: Create AI Connection in AgentFlow

Manual Setup

Admin Dashboard → AI Models → Add Model
Basic information:
- Name: Relay Business Automation
- Model ID: relay-workflow-executor
- Description: Automated business processes via Relay
API Configuration:
- Endpoint: https://api.relay.app/v1/workflows/{{workflow_id}}/execute
- Method: POST

Headers:

{
  "Authorization": "Bearer {{relay_api_key}}",
  "Content-Type": "application/json",
  "X-Relay-Version": "2024-01"
}

Request schema:

{
  "workflow_id": "{{workflow_id}}",
  "trigger_type": "webhook",
  "input_data": {
    "message": "{{message}}",
    "user_id": "{{user_id}}",
    "timestamp": "{{timestamp}}",
    "context": "{{context}}"
  },
  "execution_options": {
    "async": false,
    "timeout": 300,
    "retry_policy": "exponential_backoff",
    "max_retries": 3
  }
}

Response path: data.execution_result
Save

Step 3: Import via YAML

YAML Configuration

Create relay-workflow-config.yaml:

name: "Relay Workflow Automation"
model_id: "relay-workflow-executor"
description: "Execute Relay workflows for automated business process management"
endpoint: "https://api.relay.app/v1/workflows/{{workflow_id}}/execute"
method: "POST"

headers:
  Authorization: "Bearer {{relay_api_key}}"
  Content-Type: "application/json"
  X-Relay-Version: "2024-01"

request_schema:
  workflow_id: "{{workflow_id}}"
  trigger_type: "webhook"
  input_data:
    message: "{{message}}"
    user_id: "{{user_id}}"
    timestamp: "{{timestamp}}"
    context: "{{context}}"
  execution_options:
    async: false
    timeout: 300
    retry_policy: "exponential_backoff"
    max_retries: 3

response_path: "data.execution_result"

message_format:
  preset: "custom"
  mapping:
    role:
      source: "role"
      target: "input_data.user_role"
      transform: "lowercase"
    content:
      source: "content"
      target: "input_data.message_content"
      transform: "none"
    timestamp:
      source: "timestamp"
      target: "input_data.timestamp"
      transform: "iso8601"
    context:
      source: "context"
      target: "input_data.additional_context"
      transform: "json_stringify"
  customFields:
    - name: "relay_metadata"
      value:
        platform: "relay"
        version: "2024-01"
        execution_type: "webhook"
        environment: "production"
      type: "object"
    - name: "workflow_settings"
      value:
        timeout: 300
        retry_policy: "exponential_backoff"
        max_retries: 3
        async_execution: false
      type: "object"

suggestion_prompts:
  - "Create a workflow for automated customer onboarding process"
  - "Set up a workflow for inventory management and reorder alerts"
  - "Build a workflow for employee performance review automation"
  - "Create a workflow for automated invoice processing and approval"
  - "Set up a workflow for lead scoring and CRM updates"

Import Process

Replace placeholders with actual values
Admin Dashboard → AI Models → Import Model
Upload YAML file
Enter Relay API key
Import

Step 4: Assign to Group

Admin Dashboard → Groups
Select group (e.g., “Operations Team”)
Manage Models → Enable Relay Workflow
Set limits:
- Daily executions: 1000
- Priority: High
- Approval required: No (or Yes for sensitive operations)
Save Changes

Step 5: Use in Chat

Trigger Workflows

Chat Interface → New Conversation
Select Relay Workflow model
Send message to execute workflow

Example Scenarios

Start onboarding for new customer: Sarah Johnson, Company: TechCorp, Plan: Enterprise, Start Date: 2024-02-01

Request approval for $15,000 marketing campaign budget for Q2 social media ads

Check inventory levels for Product SKU-12345 and reorder if below 100 units

Schedule performance review for employee ID: EMP-789, Manager: John Doe, Due: Next Friday

Advanced Workflow Features

Human-in-the-Loop Approvals

Relay’s unique feature: Add approval steps

Add Approval Step

Click Add Step → Request Approval
Configure approvers
Set approval conditions

Configure Approval

{
  "approvers": ["manager@company.com", "cfo@company.com"],
  "require_all": false,
  "timeout": "24h",
  "message": "Approve {{request_details}}"
}

Handle Response

If Approved → Continue workflow
If Rejected → Send notification and end
If Timeout → Escalate to admin

AI-Powered Decision Making

Use Relay’s AI capabilities:

// AI Assist step
{
  "prompt": "Analyze this request and determine priority level",
  "input": "{{trigger.message}}",
  "model": "gpt-4",
  "output_format": {
    "priority": "string",
    "reasoning": "string",
    "recommended_action": "string"
  }
}

Multi-App Workflows

Connect multiple services:

CRM Integration

Salesforce → Search/Create contact

Communication

Slack → Send notification

Document Management

Google Drive → Create folder & files

Project Management

Asana → Create tasks

Analytics

Airtable → Log execution

Workflow Templates

1. Customer Onboarding

Trigger: API Call
Steps:
Parse customer data
Create CRM record (Salesforce)
Generate welcome email (SendGrid)
Create Google Workspace account
Setup project in Asana
Assign to success manager
Schedule kickoff call (Calendly)
Send summary to team (Slack)
Response: Onboarding status

2. Invoice Approval Workflow

Trigger: API Call
Steps:
Parse invoice details
Validate against PO (Database)
AI Review for anomalies
If > $10k → Request CFO approval
If approved → Process payment (Stripe)
Update accounting system (QuickBooks)
Send confirmation (Email)
Archive in Google Drive
Response: Payment status

3. Lead Qualification

Trigger: API Call
Steps:
  1. Extract lead information
  2. Enrich data (Clearbit)
  3. AI Scoring (GPT-4)
  4. If score > 80:
     - Add to CRM (high priority)
     - Alert sales team (Slack)
     - Schedule follow-up (Calendly)
  5. Else:
     - Add to nurture campaign (HubSpot)
  6. Log in database
Response: Lead score & next steps

Error Handling

Retry Logic

Relay automatically retries failed steps:

retry_policy:
  max_attempts: 3
  backoff_strategy: exponential
  initial_delay: 1000  # ms
  max_delay: 30000     # ms

Error Notifications

Configure alerts for failures:

error_handling:
  on_failure:
    - send_slack_alert:
        channel: "#ops-alerts"
        message: "Workflow {{workflow.name}} failed: {{error.message}}"
    - send_email:
        to: "admin@company.com"
        subject: "Workflow Error"
    - log_to_database:
        table: "workflow_errors"

Fallback Actions

Define fallback behavior:

// Condition step
if (step.failed) {
  // Execute fallback
  return {
    action: "fallback",
    notify: "admin",
    message: "Primary action failed, using fallback"
  };
}

Monitoring & Analytics

Execution Dashboard

View in Relay:

Runs: All workflow executions
Status: Success/Failed/Running
Duration: Execution time
Logs: Detailed step logs

AgentFlow Analytics

Track performance:

Analytics Dashboard → Model Usage
Filter by Relay workflows
Monitor:
- Success rate
- Average response time
- Error patterns
- Usage trends

Custom Metrics

Export data for analysis:

// At end of workflow
{
  "metrics": {
    "execution_time": "{{workflow.duration}}",
    "steps_completed": "{{workflow.steps_count}}",
    "user_id": "{{input.user_id}}",
    "outcome": "{{workflow.result}}"
  }
}

Troubleshooting

Workflow Not Triggered

Check:

API key is valid
Workflow is published (not draft)
Endpoint URL is correct
Request format matches schema

Debug: View execution log in Relay dashboard

Step Failure

Common causes:

Invalid credentials for integrated app
API rate limit exceeded
Timeout on long-running operation
Data format mismatch

Fix: Check step logs and adjust configuration

Approval Timeout

Issue: Approvers didn’t respond in timeSolutions:

Increase timeout duration
Add more approvers
Set up escalation path
Enable reminder notifications

Response Not Received

Check:

API Response step is configured
Response format matches expected schema
No errors in previous steps

Fix: Test workflow manually in Relay

Security & Compliance

API Key Management

Generate Keys

Create separate keys for different environments:

Development
Staging
Production

Rotate Regularly

Update keys every 90 days

Monitor Usage

Track API calls for anomalies

Revoke Compromised Keys

Immediately disable if breach suspected

Data Privacy

Encryption: All data encrypted in transit (TLS 1.3)
Storage: Encrypted at rest (AES-256)
Retention: Configure data retention policies
Compliance: GDPR, SOC 2, HIPAA ready

Access Control

Implement least privilege:

permissions:
  workflow_execution:
    - role: admin
      access: full
    - role: user
      access: execute_only
    - role: viewer
      access: read_logs

Best Practices

Workflow Design

Keep workflows focused and modular

Error Handling

Always add try-catch and fallbacks

Testing

Test thoroughly with edge cases

Documentation

Document purpose and data flow

Version Control

Version workflows for rollback capability

Monitoring

Set up alerts for critical workflows

Performance

Optimize for speed and efficiency

Security

Regular security audits

Relay vs Other Platforms

Feature	Relay	n8n	Make.com
Human Approvals	✅ Built-in	❌ Manual	⚠️ Limited
AI Assistance	✅ Native	⚠️ Via API	⚠️ Via API
Visual Builder	✅	✅	✅
Self-Hosted	❌	✅	❌
Pricing	Per workflow	Per execution	Per operation
Free Tier	✅ Limited	✅ 5 workflows	✅ 1K ops

Next Steps

LangChain Agents

Build AI agents with tools

Cloud Functions

Serverless automation

OpenAI Assistants

Advanced AI agents

Analytics

Monitor workflow performance

​Overview

​Prerequisites

Relay Account

API Access

Workflow Created

AgentFlow Admin

​Step 1: Setup Relay Workflow

​Create New Workflow

​Add API Trigger

​Build Workflow Logic

​Publish Workflow

​Step 2: Create AI Connection in AgentFlow

​Manual Setup

​Step 3: Import via YAML

​YAML Configuration

​Import Process

​Step 4: Assign to Group

​Step 5: Use in Chat

​Trigger Workflows

​Example Scenarios

​Advanced Workflow Features

​Human-in-the-Loop Approvals

​AI-Powered Decision Making

​Multi-App Workflows

​Workflow Templates

​1. Customer Onboarding

​2. Invoice Approval Workflow

​3. Lead Qualification

​Error Handling

​Retry Logic

​Error Notifications

​Fallback Actions

​Monitoring & Analytics

​Execution Dashboard

​AgentFlow Analytics

​Custom Metrics

​Troubleshooting

​Security & Compliance

​API Key Management

​Data Privacy

​Access Control

​Best Practices

Workflow Design

Error Handling

Testing

Documentation

Version Control

Monitoring

Performance

Security

​Relay vs Other Platforms

​Next Steps

LangChain Agents

Cloud Functions

OpenAI Assistants

Analytics

Overview

Prerequisites

Step 1: Setup Relay Workflow

Create New Workflow

Add API Trigger

Build Workflow Logic

Publish Workflow

Step 2: Create AI Connection in AgentFlow

Manual Setup

Step 3: Import via YAML

YAML Configuration

Import Process

Step 4: Assign to Group

Step 5: Use in Chat

Trigger Workflows

Example Scenarios

Advanced Workflow Features

Human-in-the-Loop Approvals

AI-Powered Decision Making

Multi-App Workflows

Workflow Templates

1. Customer Onboarding

2. Invoice Approval Workflow

3. Lead Qualification

Error Handling

Retry Logic

Error Notifications

Fallback Actions

Monitoring & Analytics

Execution Dashboard

AgentFlow Analytics

Custom Metrics

Troubleshooting

Security & Compliance

API Key Management

Data Privacy

Access Control

Best Practices

Relay vs Other Platforms

Next Steps