Pattern B: Agent as Workflow Trigger

The agent operates as a smart ingestion layer. It receives unstructured input, reasons about it, and triggers the appropriate workflow with structured parameters. You don't know upfront which workflow to run — the agent decides.

flowchart LR Input["Unstructured Input<br/>(email, document, webhook)"] --> Agent["ReAct Agent"] Agent -->|"invoice detected"| W1["Invoice Processing<br/>Workflow"] Agent -->|"support request"| W2["Support Ticket<br/>Workflow"] Agent -->|"vendor inquiry"| W3["Vendor Onboarding<br/>Workflow"] style Agent fill:#f3e8ff,stroke:#9333ea

When to Use

Input arrives in unstructured form (emails, documents, free-text)
You don't know upfront which workflow to run
Classification and extraction are required before processing
The agent acts as an intelligent router — analyzing input and dispatching

Complete Example: Document Classifier and Router

A standalone agent that receives a document, classifies it, extracts relevant fields, and triggers the correct processing workflow.

json

{
  "objective": "Classify this incoming document and route it to the correct processing workflow.\n\nDocument content:\n{{input.document_text}}\n\nSender: {{input.sender_email}}\nReceived: {{input.received_at}}",
  "tools": [
    { "type": "action", "name": "document_classifier" },
    { "type": "action", "name": "field_extractor" },
    { "type": "workflow", "name": "invoice_processing" },
    { "type": "workflow", "name": "purchase_order_processing" },
    { "type": "workflow", "name": "support_ticket_handler" },
    { "type": "workflow", "name": "contract_review" }
  ],
  "config": {
    "model": "gpt-4",
    "max_iterations": 8,
    "on_stuck": { "iterations": 3, "action": "escalate" }
  }
}

Execute via the standalone agent API:

bash

curl -X POST http://localhost:3009/agents/execute \
  -H "X-Org-Id: acme-corp" \
  -H "Content-Type: application/json" \
  -d '{
    "objective": "Classify this incoming document and route it...",
    "tools": [ ... ],
    "config": { "model": "gpt-4", "max_iterations": 8 }
  }'

Sample Reasoning Trace

text

Iteration 1:
  Thought: "I need to classify this document first."
  Action: classify_document
  Input: { "text": "Invoice #INV-2024-0891..." }
  Observation: { "category": "invoice", "confidence": 0.97 }

Iteration 2:
  Thought: "It's an invoice with high confidence. Let me extract the key fields."
  Action: extract_fields
  Input: { "text": "Invoice #INV-2024-0891...", "document_type": "invoice" }
  Observation: {
    "invoice_number": "INV-2024-0891",
    "vendor": "Acme Supplies",
    "amount": 4250.00,
    "due_date": "2026-03-15"
  }

Iteration 3:
  Thought: "I have the classification and extracted fields. Let me log progress and trigger the invoice workflow."
  Action: __log_progress__
  Input: { "message": "Document classified as invoice", "milestone": "classified" }

Iteration 4:
  Thought: "Now I'll trigger the invoice processing workflow with the extracted fields."
  Action: __run_workflow__
  Input: {
    "workflow_name": "invoice_processing",
    "input": {
      "invoice_number": "INV-2024-0891",
      "vendor": "Acme Supplies",
      "amount": 4250.00,
      "due_date": "2026-03-15",
      "sender_email": "[email protected]",
      "source": "email_ingestion"
    },
    "wait": false
  }
  Observation: { "workflow_run_id": "run_def456", "status": "running" }

Iteration 5:
  Thought: "Invoice workflow triggered. I'm done."
  Action: __complete__
  Input: {
    "answer": "Document classified as invoice (97% confidence). Triggered invoice_processing workflow (run_def456) with extracted fields.",
    "confidence": 0.97
  }

Key Properties

Workflow tools are essential — declaring { "type": "workflow", "name": "..." } gives the agent the ability to dispatch to specialized workflows
wait: false on the workflow trigger — the agent doesn't need to wait for invoice processing to complete. It classifies and routes
Standalone execution — this agent runs via POST /agents/execute, not inside a workflow. It is the entry point
Implicit tools — __log_progress__, __complete__, and __pause_for_human__ are auto-injected; no need to declare them

Scaling the Pattern

For high-volume ingestion, combine with a foreach loop in a wrapper workflow:

json

{
  "name": "batch_document_processor",
  "definition": {
    "actions": [
      {
        "type": "loop",
        "properties": {
          "mode": "foreach",
          "items_path": "@input.documents",
          "item_variable_name": "doc",
          "actions_to_execute": [
            {
              "type": "loop",
              "properties": {
                "mode": "react",
                "objective": "Classify and route: {{doc.text}}",
                "tools": [
                  { "type": "action", "name": "classify_document" },
                  { "type": "action", "name": "extract_fields" },
                  { "type": "workflow", "name": "invoice_processing" },
                  { "type": "workflow", "name": "support_ticket_handler" }
                ],
                "max_iterations": 6
              }
            }
          ],
          "max_concurrency": 5,
          "failure_strategy": "continue_on_error"
        }
      }
    ]
  }
}

→ Next: Pattern C: Agent as Orchestrator