Skip to main content
AFK applications progress through five levels of capability. Each level adds features and complexity. Start at Level 1 and move up only when you have clear signals that the current level isn’t enough.

​
The five levels

Level 1: Single Agent

One agent, one model, no tools. The simplest possible setup.
agent = Agent(name="classifier", model="gpt-5.2-mini", instructions="Classify as positive/negative/neutral.")
result = runner.run_sync(agent, user_message="Great product!")
AFK features used: Agent, Runner, run_syncGood for: Text classification, summarization, translation, simple Q&AMove up when: The agent needs to take actions or access external data

Level 2: Agent + Tools

Add typed tool functions for the agent to call.
@tool(args_model=SearchArgs, name="search", description="Search knowledge base.")
def search(args: SearchArgs) -> dict: ...

agent = Agent(name="helper", model="gpt-5.2-mini", tools=[search])
AFK features added: @tool, Pydantic models, FailSafeConfigGood for: RAG, data lookup, calculations, API integrationsMove up when: Different parts of the task need different expertise or models

Level 3: Multi-Agent Delegation

Coordinator delegates to specialist subagents.
coordinator = Agent(
    name="coordinator",
    model="gpt-5.2-mini",
    subagents=[researcher, writer, reviewer],
)
AFK features added: subagents, join policies, backpressureGood for: Complex tasks, parallel work, specialist expertise, consensusMove up when: Tasks take minutes, need async processing, or need queue-based reliability

Level 4: Queue-Backed Async

Decouple producers and consumers with task queues. Long-running jobs execute asynchronously.
queue = TaskQueue(backend="redis")
await queue.push(TaskItem(contract="runner.chat.v1", agent=agent, user_message="..."))
AFK features added: TaskQueue, TaskItem, workers, dead-letter handlingGood for: Batch processing, background jobs, retryable pipelines, high-throughputMove up when: You need cross-system communication or external agent interop

Level 5: Cross-System A2A

Agents communicate across systems using the A2A protocol with authenticated endpoints.
from afk.a2a import A2AClient
response = await a2a_client.invoke("external-agent", request=invocation_request)
AFK features added: A2AClient, A2AServer, auth providers, external adaptersGood for: Microservice agent meshes, third-party integrations, federated AI systemsThis is the ceiling — most applications don’t need Level 5.

​
Capability comparison

CapabilityL1L2L3L4L5
Text generation
Tool calling—
Multi-agent delegation——
Async processing———
Cross-system communication————
Policy engine
Observability
Evals
= essential at this level    = recommended    — = not applicable

​
Decision guide

[!TIP] Start at Level 1. The simplest system that works is the best system. Premature complexity is the most common mistake in agent design.

​
Signals to level up

SignalCurrent LevelMove to
Agent needs external data12 — Add tools
One prompt can’t cover all expertise23 — Split into specialists
Users waiting too long for results34 — Queue for async
Tasks fail and need to be retried automatically34 — Queue with DLQ
Other systems need to invoke your agents45 — Expose A2A
Third-party agents need to use your tools45 — Use MCP server

​
Next steps

Agentic Behavior

DAG orchestration, join policies, and fan-out.

Architecture

How AFK separates orchestration from execution.