[dead]
Agents need control flow, not more prompts
131–140 of 348 posts
Re: Agents need control flow, not more prompts
#132HUMANS need control flow. It's a very effective strategy that has worked wonders in healthcare
Re: Agents need control flow, not more prompts
#133that's why you need a recursive workflow that creates its own artifacts per step that can later be used for verification.
Sounds interesting, can you elaborate on your thinking? Got me curious.
Re: Agents need control flow, not more prompts
#134If we need control flows, then designing these control flows ought to be the future of agent engineering
Re: Agents need control flow, not more prompts
#135I had good success with hooks in claude code. Personally I feel this problem was common with humans as well. We added tools like husky for git commits, for our peers to push code which was linted, type checked etc. I feel hooks are integral part of your code harness, that’s only deterministic way to control coding agents.
I fully agree. Also started using husky before expanding further and created my own hooks. I can’t imagine myself using agents today without them, it would require a lot of babysitting.
Re: Agents need control flow, not more prompts
#136HUMANS need control flow. It's a very effective strategy that has worked wonders in healthcare
[dead]
Re: Agents need control flow, not more prompts
#137I wonder if a part of the problem isn't just the misapplication of LLMs in the first place. As has been mentioned elsewhere, perhaps the agent's prompt should be to write code to accomplish as much of the task in as repeatable/verifiable/deterministic a way as possible. This would hopefully include validation of the agent's output as well. The overall goal would be to keep the LLM out of doing processing that could b…
My agents often write themselves scripts. Isn't that effectively what you're asking for? Prompting for scripts can also be a useful time and accuracy tactic when you know it'll be a good fit for it.
The problem is that code it spits out on the fly is untested and untrustworthy. Identify the parts of your workflow that could be accomplished with regular code - write and unit test that code, with LLM help if you want, and use the llm as the orchestrator only.
Re: Agents need control flow, not more prompts
#138My friend, you have invented management.
Not throwing shade at anyone here but the thought has definitely crossed my mind that we are recreating SAFe but for agents when looking at some of the orchestration setups out there. I think that it is better to not force the same hierarchical processes that worked for humans in large organizations onto agents and instead look at what they need to give better results and what their failure modes look like.
Re: Agents need control flow, not more prompts
#139all caps in a prompt is a code smell. when you're typing MANDATORY, you should be writing a wrapper, not refining the prose.
Exactly! I have said this a couple of times but it was taken literally as in no capital letters or strong language. Glad to see someone else who shares this perspective.
Re: Agents need control flow, not more prompts
#140[flagged]