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

41–50 of 93 posts

Re: Building Effective AI Agents

#41

Post by samtheprogram »

jsemrau wrote: post #34
simonw wrote: post #13

Earlier quoted context omitted.

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…

"The standard for "agents" is that tools run in sequence" I don't think that this correct. Agents benefit is that they can use tools on the fly. Ideally the right tool at the right time. I.e., Which number is bigger 9.11 or 9.9 -> Agent uses calculator tool. or What is the annual 2020-2023 revenue for Apple -> Financial Statements MCP

Nothing you said contradicts the quote. When they say in sequence, they don’t mean “in a previously defined order”, they mean “not in parallel”.

Re: Building Effective AI Agents

#42

Post by rockwotj »

koakuma-chan wrote: post #32
simonw wrote: post #3

This article remains one of the better pieces on this topic, especially since it clearly defines which definition of "AI agents" they are using at the start! They use: "systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks". I also like the way they distinguish between "agents" and "workflows", and describe a bunch of useful workflow patterns. I p…

Does anyone know which AI agent framework Anthropic uses? It doesn't seem like they ever released one of their own.

Just write the for loop to react to tool calls? It’s not very much code.

Re: Building Effective AI Agents

#43

Post by mediaman »

simonw wrote: post #38
svachalek wrote: post #25

Earlier quoted context omitted.

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.

Are you using Gemini's baked in API tool calling mechanisms or are you prompting it and telling it to produce specific XML/JSON?

What do you recommend for this? I've actually had good luck having them create XML, even though you're "supposed" to use the native tool calling in a JSON schema. There seems to be far fewer issues with getting JSON syntax correct.

Re: Building Effective AI Agents

#44

Post by miki123211 »

smoyer wrote: post #14
simonw wrote: post #3

This article remains one of the better pieces on this topic, especially since it clearly defines which definition of "AI agents" they are using at the start! They use: "systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks". I also like the way they distinguish between "agents" and "workflows", and describe a bunch of useful workflow patterns. I p…

The article on the multi-agent research is awesome. I do disagree with one statement in the building effective AI agents article - building your initial system without a framework sounds nice as an educational endeavor but the first benefit you get from a good framework is the easy ability to try out different (and cross-vendor) LLMs

This is why you use a library (not a framework) that provides an abstraction over different LLMs.

I'm personally a fan of litellm, but I'm sure alternatives exist.

Re: Building Effective AI Agents

#45

Post by swyx »

simonw wrote: post #3

This article remains one of the better pieces on this topic, especially since it clearly defines which definition of "AI agents" they are using at the start! They use: "systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks". I also like the way they distinguish between "agents" and "workflows", and describe a bunch of useful workflow patterns. I p…

one half of the authors of Building Effective Agents also came by AIE to do a well received talk version of this article: https://www.youtube.com/watch?v=D7_ipDqhtwk

Re: Building Effective AI Agents

#46

Post by simonw »

mediaman wrote: post #43
simonw wrote: post #38

Earlier quoted context omitted.

Are you using Gemini's baked in API tool calling mechanisms or are you prompting it and telling it to produce specific XML/JSON?

What do you recommend for this? I've actually had good luck having them create XML, even though you're "supposed" to use the native tool calling in a JSON schema. There seems to be far fewer issues with getting JSON syntax correct.

I'm using their native tool calling: https://github.com/simonw/llm-gemini/commit/a7f1096cfbb73301... - it's been working really well for me so far.

Re: Building Effective AI Agents

#47

Post by fennecbutt »

iLoveOncall wrote: post #19

> These frameworks make it easy to get started by simplifying standard low-level tasks like calling LLMs, defining and parsing tools, and chaining calls together. However, they often create extra layers of abstraction that can obscure the underlying prompts and responses, making them harder to debug. They can also make it tempting to add complexity when a simpler setup would suffice. > We suggest that developers star…

I suppose langflow also falls into this bucket.

I still think it has a definite use case in regularising all of your various flows into a common format.

Sure, I could write some code to get SD to do all the steps to generate an image, or write some shader code. But it's so much more organised to use comfy-UI, or a shader graph, especially if I have n>1 flows/tasks, and definitely while experimenting with what I'm building.

Re: Building Effective AI Agents

#48

Post by bgwalter »

They are so desperate that they start writing about LLM patterns now. Is an agentic LLM framework a Code Factory? Or perhaps a Code Factory Factory?

Or is it like a burrito (meme explanation of Monads when they were the latest hype)?

Re: Building Effective AI Agents

#50

Post by ankit219 »

koakuma-chan wrote: post #32
simonw wrote: post #3

This article remains one of the better pieces on this topic, especially since it clearly defines which definition of "AI agents" they are using at the start! They use: "systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks". I also like the way they distinguish between "agents" and "workflows", and describe a bunch of useful workflow patterns. I p…

Does anyone know which AI agent framework Anthropic uses? It doesn't seem like they ever released one of their own.

From what it looks like, it's one main LLM (you are sending query to - orchestrator) which calls other LLMs via tool calls. The tools are capable of calling llms too, and can have specific instructions, but mostly just the orchestrator deciding what they should be researching on, and assigns them specific subqueries. There is a limited depth / levels of search queries too, you should see the prompt they use[1]

One cool example of this in action is seen when you use claude code and ask it to search something. In a verbose setting, it calls an MCP tool to help with search. The tool returns summary of the results with the relevant links (not the raw search result text). A similar method, albeit more robust, is used when Claude is doing deep research as well.

[1]: https://github.com/anthropics/anthropic-cookbook/blob/main/p...

Post reply on HN