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

Building Effective AI Agents

anthropic.com

Post reply on HN
Print view View original

21–30 of 93 posts

Re: Building Effective AI Agents

#21

Post by 0x457 »

AvAn12 wrote: post #10

How do agents deal with task queueing, race conditions, and other issues arising from concurrency? I see lots of cool articles about building workflows of multiple agents - plus what feels like hand-waving around declaring an orchestrator agent to oversee the whole thing. And my mind goes to whether there needs to be some serious design considerations and clever glue code. Or does it all work automagically?

I can only talk about Codex web interface, I had a very detailed refactoring plan for a project it was too long to complete in one go, so used "ask" feature to split it up into multiple task and group them by "which tasks can be executed concurrently".

It split them up in a way they would be split up in real life, but in real life there is an assumption that people working on tasks going to communicate with each other. The way it generates tasks resulted in HUGE loss of context (my plan was hella detailed).

I was willing to spend a few more hours trying to make it work rather than doing the work myself. I've opened another chat and split it up into multiple sequential tasks, with a detailed prompt for each task (why, what, how, validation, update documentation reminder etc).

Anyway, orchestrator might work on some super simple tasks, much smaller tasks than those articles make you believe.

Re: Building Effective AI Agents

#22

Post by chaosprint »

Half a year has passed, and it feels like a long time in the field of AI. I read this article repeatedly a few months ago, but now I think the development of Agent has obviously reached a bottleneck. Even the latest gemini seems to have regressed.

Re: Building Effective AI Agents

#23

Post by m3kw9 »

chaosprint wrote: post #22

Half a year has passed, and it feels like a long time in the field of AI. I read this article repeatedly a few months ago, but now I think the development of Agent has obviously reached a bottleneck. Even the latest gemini seems to have regressed.

They have hard time solving prompt issues injection and that’s a one of the bottle necks

Re: Building Effective AI Agents

#24

Post by rdedev »

AvAn12 wrote: post #10

How do agents deal with task queueing, race conditions, and other issues arising from concurrency? I see lots of cool articles about building workflows of multiple agents - plus what feels like hand-waving around declaring an orchestrator agent to oversee the whole thing. And my mind goes to whether there needs to be some serious design considerations and clever glue code. Or does it all work automagically?

This is why I am leaning towards making the llm generate code that calls operates on took calls instead of having everything in JSON.

Huggingfaces's smolagents library makes the llm generate python code where tools are just normal python functions. If you want parallel tools calls just prompt the llm to do so. It should take care of synchronizing everything. Ofcourse there is the whole issue around executing llm generated code but we have a few solutions for that

Re: Building Effective AI Agents

#25

Post by svachalek »

simonw wrote: post #13
AvAn12 wrote: post #10

How do agents deal with task queueing, race conditions, and other issues arising from concurrency? I see lots of cool articles about building workflows of multiple agents - plus what feels like hand-waving around declaring an orchestrator agent to oversee the whole thing. And my mind goes to whether there needs to be some serious design considerations and clever glue code. Or does it all work automagically?

The standard for "agents" is that tools run in sequence, so no need to worry about concurrency. Several models support parallel tool calls now where the model can say "Run these three tools" and your harness can chose to run them in parallel or sequentially before passing the results back to the model as the next step in the conversation. Anthropic are leaning more into multi-agent setups where the parent agent might…

I'm not sure we're at "great" yet. Gemini 2.5 pro fails maybe 50% of the time for me at even generating a syntactically successful tool call.

Re: Building Effective AI Agents

#26

Post by 0x457 »

deadbabe wrote: post #11

When an AI agents completes a task, why not have the AI agent save the workflow used to accomplish that task so the next time it sees a similar input it feeds it to a predefined series of tools to avoid any LLM decision making in between tool calls? And then eventually, with enough sample inputs, create simple functions that can recognize what tools should be used to process a type of input? And only fallback to an L…

You somewhat can do this. I use neo4j as a knowledge database for agents, and it has processes and tasks described.

Re: Building Effective AI Agents

#28

Post by EGreg »

chaosprint wrote: post #22

Half a year has passed, and it feels like a long time in the field of AI. I read this article repeatedly a few months ago, but now I think the development of Agent has obviously reached a bottleneck. Even the latest gemini seems to have regressed.

What exactly makes them regress?

Why can’t they just fork swarms of themselves, work 24/7 in parallel, check work and keep advancing?

Re: Building Effective AI Agents

#29

Post by daxfohl »

pyman wrote: post #16
cmsparks wrote: post #12

Earlier quoted context omitted.

Frankly, it's pretty difficult. Though, I've found that the actor model maps really well onto building agents. An instance of an actor = an instance of an agent. Agent to agent communication is just tool calling (via MCP or some other RPC) I use Cloudflare's Durable Objects (disclaimer: I'm biased, I work on MCP + Agent things @ Cloudflare). However, I figure building agents probably maps similarly well onto any acto…

Should the people developing AI agent protocols be exploring decentralised architectures, using technologies like blockchain and peer-to-peer networks to distribute models and data? What are the trade-offs of relying on centralised orchestration platforms owned by large companies like Amazon, Cloudfare or NVIDIA? Thanks

That's more of a hobbyist thing I'd say. Corporations developing these things will of course want to use some centralized system that they trust. It's more efficient, they have more control over it, it's easier for average people to use, etc.

A decentralized thing would be more for individuals who want more control and transparency. A decentralized public ledger would make it possible to verify that your agent, the agents it interacts with, and the contents of their interactions have not been altered or compromised in any way, whereas a corporate-owned framework could not provide the same level of assurance.

But technically, there's no advantage I can think of for using a public distributed ledger to manage interactions. Agent tasks are pretty ephemeral, so unlike digital currency, there's not really a need to maintain a complete historical log of every action forever. And as far as providing tools for dealing with race conditions, blockchain would be about the least efficient way of creating a mutex imaginable. So technically, just like with non-AI apps, cetralized architecture is always going to be a lot more efficient.

Re: Building Effective AI Agents

#30

Post by amelius »

EGreg wrote: post #28
chaosprint wrote: post #22

Half a year has passed, and it feels like a long time in the field of AI. I read this article repeatedly a few months ago, but now I think the development of Agent has obviously reached a bottleneck. Even the latest gemini seems to have regressed.

What exactly makes them regress? Why can’t they just fork swarms of themselves, work 24/7 in parallel, check work and keep advancing?

Because they are not intelligent. (And this is a good definition of it).
Post reply on HN