The conversation

mafrieseHNSource author
Lessons learnedExperience excerpt · English

- I built a system where context (+ the current state + goal) is properly structured and coding …

… - I built a system where context (+ the current state + goal) is properly structured and coding agents only get the information they actually need and nothing more. You wouldn’t let your product manager develop your backend and I gave the backend dev only do the things it is supposed to and nothing more. If an agent crashes (or quota limits are reached), the agents can continue exactly where the other agents left off. - Agents are ”fighting against” each other to some extend? The Architect tries to design while the CAB tries to reject. - Granular control. I wouldn’t call “the manager” _a deterministic state machine that is calling probabilistic functions_ but that’s to some extent what it is? The manager has clearly defined tasks (like “if file is in 01_design —> Call Architect) Here’s one example of an agent log after a feature has been implemented from one of the older codebases: https://pastebin.com/7ySJL5Rg

Original discussionClaude Code's new hidden feature: Swarms335 source comments · at import
4

What was this responding to?

Parent context · original excerpt

Community replies 0

No community replies yet. Add your perspective.

Replies from the source 4

Direct replies available in this import. Original-language excerpts.

ST
stavrosHN

What OpenCode primitive did you use to implement this? I'd quite like a "senior" Opus agent that lays out a plan, a "junior" Sonnet that does the work, and a senior Opus reviewer to check that it agrees with the plan.

Full original
OV
overfeedHN

> [...]coding agents only get the information they actually need and nothing more Extrapolating from this concept led me to a hot-take I haven't had time to blog about: Agentic AI will revive the popularity of microservices. Mostly due to the deleterious effect of context size on agent performance.

Full original
NO
nobody_r_knowsHN

I'm confused when you say you have a manager, scrum master, archetech, all supposdely sharing the same memory, do each of those "employees" "know" what they are? And if so, based on what are their identities defined? Prompts? Or something more. Or am I just too dumb to understand / swimming against the current here. Either way, it sounds amazing!

Full original
IM
imiricHN

Isn't all this a manual implementation of prompt routing, and, to a lesser extent, Mixture of Experts? These tools and services are already expected to do the best job for specific prompts. The work you're doing pretty much proves that they don't, while also throwing much more money at them. How much longer are users going to have to manually manage LLM context to get the most out of these tools? Why is this still a problem ~5 years into this tech?

Full original
Continue on Hacker News

Respect different perspectives. Share concrete experiences.

Sign in to post, reply, repost, and quote.