[zh2408]

Let me clarify: this tutorial focuses on the technical internal implementation of the agent (e.g., OpenAI agent, Pydantic AI, etc.), rather than the UI/UX of the agent-based products that end users interact with.

[yed]

The newest generation of agents[0] aren't implemented this way; the model itself is trained to make decisions and a plan of action rather than an explicitly programmed workflow tree.

[0] https://openai.com/index/computer-using-agent/

[zh2408]

I think you’re referring to function calling: https://platform.openai.com/docs/guides/function-calling

This still returns a string. You need to explicitly program the branch to the right function. For example, check out how OpenAI Agents, released a week ago, rely on a workflow: https://github.com/openai/openai-agents-python/blob/48ff99bb...

[yed]

No I'm referring to the newest generation of agentic models one of which I linked to. These are not fully released but it is where the newest generation of research is headed.

[zh2408]

It's hard for me to comment on something not open sourced

[nileshtrivedi]

That remains to be seen. Manus, a standard agent built with Claude 3.7, outperforms o3 agentic model on the GAIA benchmark.

[throwaway7783]

Operator/Computer Use is a bridge until we no longer need any tools at all

[achierius]

What gives you any confidence in that transition happening in the best future?

[campbel]

That's what I am talking about as well. The low-level implementation of an agent isn't necessarily a rigid graph, and I'd actually argue its explicitly not this.

[zh2408]

The current implementations of Agents, e.g., OpenAI agents released last week, are based on graph (workflow): https://github.com/openai/openai-agents-python/blob/48ff99bb...

Not sure about Cursor you mentioned as its agent is not open sourced.

[campbel]

This link is also referring to the nodes as agents. So its a system of agents interacting to product an outcome. I'm not saying this system is bad, just that I think it deserves another name rather than calling the whole system an "Agent". It's many agents working in a coordinated fashion.

[zh2408]

No. It's not many agents in the workflow. It's not an agent per node.

The whole workflow and the Runner class is for one agent.

Check out this line: https://github.com/openai/openai-agents-python/blob/48ff99bb...

A single `run_agent` is implemented based on the Runner class and workflow. So usually the workflow is for one agent (unless there is handoff).

[campbel]

They define it in the same file https://github.com/openai/openai-agents-python/blob/48ff99bb...

> An agent is an AI model configured with instructions, tools, guardrails, handoffs and more.

Agents can hand off to other agents, but even the hand-off is decided by the agent itself, not a pre-defined orchestration.