This is, at least in part, the promise of frameworks like DSPy and PydanticAI. They allow you to structure LLM calls within the broader control flow of the program, with typed inputs and outputs. That doesn’t fix non-determinism, hallucinations, etc., but it does allow you to decompose what it is you’re trying to accomplish and be very precise about when an LLM is called and why.
Agents need control flow, not more prompts
61–70 of 348 posts
Re: Agents need control flow, not more prompts
#62Yes. Humans are also unreliable and nondeterministic (though certainly more reliable). Accordingly we have built software dev practices around this. I imagine it would be super useful for example to have a "TDD enforcer": Phase 1: only test files may be altered, exactly one new test failure must appear. Phase 2: only code files may be altered. The phase is cleared when the test now succeeds and no other tests fail. I…
I've been busy building and dogfooding open-artisan for my own development purposes. I've diverged quite a bit from main and am hoping to merge some of those changes back soon. It's basically an OpenCode plugin that forces open-code token-hungry state machine that tries to map the engineering process I follow, exposing only valid tools and states at every step of development. If you're interested, in following along or trying it out, it's available here:
https://github.com/yehudacohen/open-artisan/
Hopefully, I'll merge in my large structural changes in the next couple of weeks. These structural changes will enhance the state machine meaningfully, as well as adding support for hermes agenet.
Re: Agents need control flow, not more prompts
#63[flagged]
Re: Agents need control flow, not more prompts
#64Afaict all harnesses are wrong in this respect, some of them deeply so. Slash commands, for instance, are a misfeature. I should never have to wait for the chatbot finish a turn so that I can check on the status of my context window or how much money I've spent this session. Control should be orthogonal to the chat loop. Even things that have nothing to do with controlling the text generator's input and output are en…
I use the Codex desktop app.
In the GUI I can see the context indicator and usage stats.
It also makes it easier to jump between conversations and see the updates.
Sometimes I use Claude Code or opencode in the terminal, and my experience is much poorer compared to the Codex desktop app.
Re: Agents need control flow, not more prompts
#65Or maybe, just maybe, LLMs do not run deterministicly and that is ok?
In the real world almost nothing runs like that - only software and even that has a lot of failures.
So perhaps rather than trying to make agents run deterministicly the goal is to assume some failure rate and find compensation control around it.
Re: Agents need control flow, not more prompts
#66I agree with the sentiment, but I think the conclusion should be altered. When you hit the limit of prompting, you need to move from using LLMs at run time to accomplish a task to using LLMs to write software to accomplish the task. The role of LLMs at run time will generally shrink to helping users choose compliant inputs to a software system that embodies hard business rules.
I've seen cases where models will get stuck in a particular mode of problem solving and need a nudge to tell them to move to a new mode. For example, instead of trying to massage a bunch of system service configs to handle hot-plug/unplug of an audio stream, what I really needed was to just write a couple dozen lines of Python to handle stuff.
I just had Claude write itself a couple shell scripts to handle a bunch of common cases (like running tests) in my workflow where it just couldn't figure it out efficiently. Now it just runs those tools and sets things up instead of spinning in circles for half an hour.
Every time it tries to ask me if it can run some one-off crazy shell or python one-liner to do something, I've started asking myself if I should have it write a tool I can auto-approve instead.
Re: Agents need control flow, not more prompts
#67I feel like people forget that they're still allowed to program. You're still allowed to create workflows tying together LLMs and agents if you want. Almost all the tools and technology that existed before LLMs are still available to be used.
Re: Agents need control flow, not more prompts
#68I’ve been building a small ‘agent’ using copilot at work, partly a learning exercise as well as testing it in a small use case.
My personal opinion is that AI and agents are being misrepresented… The amount of setup, guidance and testing that’s required to create smarter version of a form is insane.
At the moment my small test is: Compressed instructions (to fit within the 8k limit) 9 different types of policies to guide the agent (json) 3 actual documents outlining domain knowledge (json) 8 Topics (hint harvesting, guide rails, and the pieces of information prepared as adaptive cards for the user) 3 Tools (to allow for connectors)
The whole thing is as robust as I can make it but it still feels like a house of cards and I expect some random hiccup will cause a failure.
Re: Agents need control flow, not more prompts
#69It's the right direction, but control flow introduces limitations within a system that is quite adaptable to dynamic situations. The more control flow you try to do, the more buggy edge cases that pop up if done poorly. Still have yet to see a universal treatment that tackles this well.
I would just reverse the architecture of the whole system. Build a classic deterministic program, and use LLMs as heuristics adapting the system to the environment - the functions that you call on the 'if's and 'switch' statements to decide where the system should go.
I see this as the most robust way to build a predictable system that runs in a controlled way while taking advantage of probabilistic AIs while reducing the impact of their alucinations.
LLMs simply can't be trusted to follow instructions in the general case, no matter how much you constraint them. The power of very large probabilistic models is that they basically solved the _frame problem_ of classic AI: logical reasoning didn't work for general tasks because you can't encode all common sense knowledge as axioms, and inference engines lost their way trying to solve large problems.
LLMs fix those handicaps, as they contain huge amounts of real world knowledge and they're capable of finding facts relevant to the problem at hand in an efficient way. Any autonomous system using them should exploit this benefit.
Re: Agents need control flow, not more prompts
#70How is this not obvious to everyone? It's like people forgot how to engineer.