Building a Multi-Agent System from Scratch: Architecture Patterns

kadhar.dev

103 points by kadharmfn 2 days ago


pss314 - 2 days ago

I liked going thru Stanford CS146S: How always-on agents work

Lecture recording: https://www.youtube.com/watch?v=L1OBRtfPS34

Slides: https://drive.google.com/file/d/1b8WiBk_lcB3ue-jZMLijSUMLj6S...

Note: The lecture talks mostly on always-on agents and not necessarily multi-agent system.

phainopepla2 - 2 days ago

Perhaps I'm being uncharitable, but when I open up a page that was obviously created by Claude, I just close it again.

empath75 - 2 days ago

If you leave "The Honest Summary" in anything Claude wrote, I am not going to read any of it, shows a complete lack of care or interest in what you are doing.

I don't care if you are having Claude write something for you, but I feel like I spent more time writing these two sentences than this person put into this post.

brkomir - 2 days ago

I usually run 4-5 claude sessions in parallel on the same branch, each with its own working plan or work item. They coordinate almost in real time, leaving messages in a shared queue and picking them up every 30 seconds. What keeps them from stepping over each other's work is a commit script that allows only staged changes from one session to be committed at a time.

Where it actually pays off to have separate sessions is the code review. Every code change that affects how the app behaves is checked by a session that didn't write the change. Some numbers: 4,454 verdicts on 4,471 commits since September. About four in five first reviews found something, and about half asked for changes.

bill10 - 2 days ago

Claude code is good enough now to call subagent and manage them itself, right?

albertgoeswoof - 2 days ago

What’s an example of a multi agent system that people are using?

beardbandit - a day ago

Is it just me or are many of these things just common sense to someone that has designed systems before? I’ve found zero help with many of these AI-related blogs and articles. The only novel ones that actually turn into anything actionable or insightful are the first party articles from the frontier companies themselves…

bob1029 - 2 days ago

Sub agents are significantly more useful than multi agents.

Wrap a nested prompt with a tool call that is invoked by the caller prompt. That is the answer to all your suffering. You can repeat this for as many layers of invocation as you desire. You can layer determinism and non-determinism as much as you like in whatever orders you see fit with additional alignment, retry policies, logging, etc.

Agents running concurrently will not go any faster than one well-designed hierarchical agent system.

Imagine the simple task of incrementing a global counter. That would be my #1 benchmark. If you can demonstrate a MAS can increment that counter faster than a single agent can (monotonically without skipping), then I will happily delete 100% of the AI-related code I've authored and start over using your ideas.

latentsea - 2 days ago

The Honest Summary

FLeXMurphy - 2 days ago

I remember all these topics being discussed... well over 25 years ago, though I'm sure they are much older than that.

nzjrs - 2 days ago

Slop

kadharmfn - 2 days ago

[flagged]

RetardedBastard - 2 days ago

[dead]

cush - 2 days ago

Does anyone else open sites with this default claude code theme and immediately close them?