Why the OpenAI Agents SDK keeps Agent, Handoff, and Runner as its only three primitives

Attempt it

Larger agent frameworks ship dozens of abstractions (graph, node, edge, state, reducer, memory, manager, executor, planner) because they want to cover every topology and every coordination pattern. That gives you power and a learning curve.

The Agents SDK bets that 80 percent of production multi-agent workloads are 'a few agents that hand off to each other,' and that the framework's job is to make that case beautiful and stay out of the way. Agent is the persona plus tools unit, Handoff is the peer transfer primitive baked as a tool call, Runner is the loop that runs an agent and executes the tool and handoff calls until termination. Anything beyond that (parallel fan-out, state machines, durable resume) you build yourself or use a different framework. The smaller surface means lower onboarding cost and fewer ways to assemble the system wrong; the trade is less out of the box power.

Your answer

Quick reference

TL;DR

Three primitives cover the 'a few agents that hand off to each other' case beautifully and stay out of the way; anything beyond it you build yourself or pick a different framework.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine the kitchen aisle. Some gadget brands sell you 40 different specialised tools (an avocado slicer, a strawberry huller, a banana peeler). Others sell you a really good knife and trust you with the rest. The Agents SDK is the really good knife brand. It says: most agent work is one agent doing the job until it hands the task to a teammate; we will make that one motion clean and let you bring your own kitchen for everything else. The trade is honest. You give up shelves of specialised gadgets in exchange for fewer ways to cut yourself.

Key concepts

Multi-Agent Systems

Quick scan · 2–4 min

Everything important, quickly.

3 to 5 min: name the three primitives, explain the workload bet, contrast with LangGraph and AutoGen 0.4 surface areas, name when each framework wins.

Code example

python

from agents import Agent, Runner

billing = Agent(name="billing",
    instructions="Handle billing questions.",
    tools=[lookup_invoice, issue_refund])

tech = Agent(name="tech",
    instructions="Handle technical issues.",
    tools=[search_kb, escalate_to_oncall])

triage = Agent(name="triage",
    instructions="Route the user to the right specialist.",
    handoffs=[billing, tech])

result = Runner.run_sync(triage, "My invoice looks wrong")
print(result.final_output)

Real-world examples

Real products, models, and research that use this idea.

OpenAI's own documentation example builds a triage agent that hands off to billing, refund, and tech-support specialists.
Klarna and Stripe-style customer-support routing fits the agent plus handoff pattern cleanly.
Hugging Face's smolagents adopted a similar peer-handoff idiom via ManagedAgent wrappers.
LangGraph offers create_swarm as the corresponding shape on its typed state graph runtime.
Anthropic's published agent design guidance recommends the handoff as tool call pattern as a portable production idiom.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you add structured shared state across multiple agents in the SDK?

Sign in or go Pro to see the approach for this follow-up.

QWhat is the safety story for peer handoffs in the SDK?

Sign in or go Pro to see the approach for this follow-up.

QHow does the SDK compare to LangGraph's create_swarm prebuilt?

Sign in or go Pro to see the approach for this follow-up.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.