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

Multi-Agentic Software Development Is a Distributed Systems Problem

kirancodes.me

Post reply on HN
Print view View original

41–50 of 75 posts

Re: Multi-Agentic Software Development Is a Distributed Systems Problem

#42

Post by airstrike »

21asdffdsa12 wrote: post #32
airstrike wrote: post #21

Earlier quoted context omitted.

"Nothing" prevents it other than the fact that an agent doesn't really have memory and has a pretty limited context, hallucinates information, mistakes metadata with data, and so on. The path forward is always one that starts from the assumption that it will go wrong in all those different ways, and then builds from there

So one hub architect agent for overview- which generates tokens for the spoke agent and receives architectural problem reports from spoke agents?

That seems to be the most common "fix" people deploy today, but it's still structurally flawed due to inherent limitations in LLMs.

Re: Multi-Agentic Software Development Is a Distributed Systems Problem

#43

Post by siliconc0w »

My workflow uses a thorough design broken down into very specific tasks, agent mail, and a swarm of agents in a ralph loop to burn down tasks. Agents collaborate with mail pretty well and don't seem to need layers of supervision. If the tasks are well specified and your design is thought through, especially how to ensure the agents can self-validate - it seems to work pretty well.

I wrote an article on this if you're interested: https://x.com/siliconcow/status/2035373293893718117

Re: Multi-Agentic Software Development Is a Distributed Systems Problem

#44

Post by tomwheeler »

jimmypk wrote: post #41

[flagged]

> Even if a failed agent activity retries correctly at the infrastructure layer, the LLM re-invocation produces a different output.

In Temporal, an Activity won't be executed again provided that Activity completion is recorded to the event history.

If the application crashes, its state is recreated using results from the history (i.e., the ones from the invocation that happened prior to the crash). Thus, the non-deterministic nature of LLM calls doesn't affect the application because each effectively only happens once.

Re: Multi-Agentic Software Development Is a Distributed Systems Problem

#46

Post by mrothroc »

binyu wrote: post #36
mrothroc wrote: post #31

I've been running a multi-agent software development pipeline for a while now and I've reached the same conclusion: it's a distributed systems problem. My approach has been more pragmatic than theoretical: I break work into sequential stages (plan, design, code) with verification gates. Each gate has deterministic checks (compile, lint, etc) and an agentic reviewer for qualitative assessment. Collectively, this looks…

Interesting perspective. While the analogy may be somewhat intuitive, distributed computing exhibit a wider and more diverse set of challenges imo. Example: Synchronization in naturally async environments, consensus, failure-safe system, etc.

Agreed that full consensus is overkill.

But I think the coordination problem is subtler than version control implies. In the (plan, design, code) pipeline they aren't collaborating on the same artifact. They're producing different artifacts that are all expressions of the same intent in different spaces: a plan in natural language, a design in a structured spec, code in a formal language.

Different artifacts which are different projections in different Chomsky levels but all from the same thing: user intent.

The coordination challenge is keeping these consistent with each other as each stage transforms the prior projection into the new one. That's where the gates earn their place: they verify that each transformation preserves the intent from the previous stage.

Re: Multi-Agentic Software Development Is a Distributed Systems Problem

#48

Post by Tade0 »

falcor84 wrote: post #28
Tade0 wrote: post #23

Earlier quoted context omitted.

Sohnds like a great way to fill up the context before you even start.

Yes, what's your point? That is literally what it does - it adds relevant knowledge to the prompt before generating a response, in order to ground it me effectively.

My point is that this doesn't scale. You want the LLM to have knowledge embedded in its weights, not prompted in.
Post reply on HN