Depends on the use case
Agents need control flow, not more prompts
191–200 of 348 posts
Re: Agents need control flow, not more prompts
#192I've been thinking about this a lot actually. It can almost be related to the conversation about specialization. The more specialized a model is required to be, the less capable it seems to be at a foundational level, where as if you just aim towards a liiitle bit of abstraction, you might get the best of both worlds.
Here's a pretty specific example of what I mean, but maybe food for thought:
Podcast (20 minute digest): https://pub-6333550e348d4a5abe6f40ae47d2925c.r2.dev/EP008.ht...
Re: Agents need control flow, not more prompts
#193Build CLIs your agents call, that scaffold what you want, and lint so it actually does achieves your intended design.
Markdown files are a good reference but they are a weak enforcement tool and go stale easily.
Avoid burying yourself in more skills docs you’re not even writing yourself and probably never even read. Focus that toward deterministic tooling. (Not that skills or prompts are bad, I agree a meta skill that tells an agent what subagents and what order to run is useful)
Re: Agents need control flow, not more prompts
#1941000% 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: "…
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 make codex do everything through a giant `justfile`. Simple, greppable, self-documenting, works great, and I don’t even need to read it.
Re: Agents need control flow, not more prompts
#1951000% 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: "…
> This started breaking down after ~30 files. Sometimes it would miss a file. Sometimes it would triple-test a bundle of files and take 10 minutes instead of 3. An error in one file would convince it it needs to re-test four previous files, for no reason. It was very frustrating. Sorry, you thought a prompt was a suitable replacement for a testing suite?
hey man it works great barely and also costs a bunch of money everytime we run it. we also can't trust the results, relax.
Re: Agents need control flow, not more prompts
#1961000% 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: "…
[flagged]
Re: Agents need control flow, not more prompts
#1971000% 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
No you didn't
"What we're not open sourcing (yet) is the runtime. "
Re: Agents need control flow, not more prompts
#198If 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 determini…
"conversation.send_message("Write 3 facts about the current project into FACTS.txt.")"
why tf would i ever need this
Re: Agents need control flow, not more prompts
#199Build CLIs your agents call, that scaffold what you want, and lint so it actually does achieves your intended design. Markdown files are a good reference but they are a weak enforcement tool and go stale easily. Avoid burying yourself in more skills docs you’re not even writing yourself and probably never even read. Focus that toward deterministic tooling. (Not that skills or prompts are bad, I agree a meta skill tha…
lol so write an actual deterministic program? we're close to full circle
Re: Agents need control flow, not more prompts
#200> Imagine a programming language where statements are suggestions and functions return “Success” while hallucinating. Reasoning becomes impossible; reliability collapses as complexity grows. This is essentially declarative programming. Most traditional programming is imperative, what most developers are used to - I give the exact set of instructions and expect them to be obeyed as I write them. Agents are way more de…
> This is essentially declarative programming. I think it's step more-abstract that that, we're doing... How about " narrative programming"? (Though we could debate whether "programming" is still an applicable word.) Yes, it may look like declarative programming, but it's within an illusion: We aren't aren't actually describing our goals "to" an AI that interprets them. Instead, there's a story-document where our hum…
I dont hate that distinction, I just think a lot of people are approaching this from an imperative framework that might not fit.