Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agents need control flow, not more prompts

bsuh.bearblog.dev

Post reply on HN
Print view View original

151–160 of 348 posts

Re: Agents need control flow, not more prompts

#151

Post by gck1 »

As someone who went full circle prompt-enforcement > deterministic flow > prompt-enforcement, I disagree.

The reason why "DO NOT SKIP" fails is because your agent is responsible for too many things and there's things in context that are taking away the attention from this guidance.

But nobody said the agent that does enforcement must be the same agent that builds. While you can likely encode some smart decision making logic in your deterministic control flow, you either make it too rigid to work well, or you'll make it so complex that at that point, you might as well just use the agent, it will be cheaper to setup and maintain.

You essentially need 3 base agents:

- Supervisor that manages the loop and kicks right things into gear if things break down

- Orchestrator that delegates things to appropriate agents and enforces guardrails where appropriate

- Workers that execute units of work. These may take many shapes.

Re: Agents need control flow, not more prompts

#154

Post by crsn »

eth415 wrote: post #6

agreed - this is what we’ve been trying to build at scale. https://github.com/salesforce/agentscript

Ditto Ethan's point -- and hundreds of customers tell us it works very well. We'd value more feedback from this community, not just the Salesforce/Agentforce customer base!

Re: Agents need control flow, not more prompts

#156

Post by crsn »

827a wrote: post #100

1000% agree. I am increasingly hesitant to believe Anthropic's continual war drum of "build for the capabilities of future models, they'll get better". We've got a QA agent that needs to run through, say, 200 markdown files of requirements in a browser session. Its a cool system that has really helped improve our team's efficiency. For the longest time we tried everything to get a prompt like the following working: "…

Our team at Agentforce recently open-sourced our solution to this and we've gotten very valuable feedback -- would love to hear from more of you about it: https://github.com/salesforce/agentscript

Re: Agents need control flow, not more prompts

#158

Post by awongh »

827a wrote: post #100

1000% agree. I am increasingly hesitant to believe Anthropic's continual war drum of "build for the capabilities of future models, they'll get better". We've got a QA agent that needs to run through, say, 200 markdown files of requirements in a browser session. Its a cool system that has really helped improve our team's efficiency. For the longest time we tried everything to get a prompt like the following working: "…

The other part of the question is exactly when the "build for the capabilities of future models" becomes the present.

Looking at the Mythos benchmarks, it doesn't seem like the models are that close to being truly reliable for agentic tasks.

Is it a year away, or five? That's a big difference in deciding what to build today.

Re: Agents need control flow, not more prompts

#159

Post by shripadt »

tonylucas wrote: post #148
sharperguy wrote: post #146

Earlier quoted context omitted.

So I wonder, if a more powerful agent harness could have the agent basically write and exectute its own deteministic code, which when executed, spawns sub agents for each of the subtasks? So far we've seen agents spawn subagents directly, but that still means leaving the final flow control to the non-deterministic orchestrator model, and so your case is a perfect example of where it would probably fail.

I've been working on an integrated deterministic/agent integrated system for a few months now. It basically runs an AI step to build a plan, which biases towards deterministic steps as much as possible but escalates back to AI when it needs to (for AI only capabilities or deterministic failures) so effectively (when I perfect it, I'm about 90% there) it can bounce back and forward as needed with deterministic steps l…

[flagged]

Re: Agents need control flow, not more prompts

#160

Post by rbren »

If you're interested in driving coding agents with code, check out the OpenHands Software Agent SDK [1]

We need to define agents in code, and drive them through semi-deterministic workflows. Kick subtasks off to agents where appropriate, but do things like gather context and deal with agent output deterministically.

This is a massive boost in accuracy, cost efficiency, AND speed. Stop using tokens to do the deterministic parts of the task!

[1] https://github.com/OpenHands/software-agent-sdk

Post reply on HN