How Tasks Flow Between Agents

In A2A, work is organized around Tasks - structured units of work that flow between a Client Agent and a Remote Agent.

Task State Machine

┌─────────┐     ┌────────────┐     ┌──────────┐
│ CREATED │────▶│ IN_PROGRESS│────▶│COMPLETED │
└─────────┘     └──────┬─────┘     └──────────┘
                       │
                  ┌────▼────┐
                  │ BLOCKED │ (needs input from client)
                  └────┬────┘
                       │
                  ┌────▼────┐
                  │ FAILED  │
                  └─────────┘

Task Lifecycle Example

// 1. Client creates a task
POST /a2a/tasks
{
  "skill": "book_flight",
  "input": {
    "origin": "London",
    "destination": "New York", 
    "date": "2026-05-15"
  }
}

// 2. Remote agent processes and responds
{
  "taskId": "task_abc123",
  "status": "IN_PROGRESS",
  "updates": [
    { "type": "status", "message": "Searching 5 airlines..." },
    { "type": "status", "message": "Found 12 flights" }
  ]
}

// 3. Agent might need clarification (BLOCKED)
{
  "status": "BLOCKED",
  "question": "Do you prefer direct flights only or include layovers?",
  "options": ["direct_only", "include_layovers"]
}

// 4. Client responds, agent completes
{
  "status": "COMPLETED",
  "result": {
    "flight": "BA177",
    "price": "$542",
    "departure": "09:15"
  }
}

Key A2A Interaction Patterns