←back to thread

Building Effective AI Agents

(www.anthropic.com)
543 points Anon84 | 9 comments | 17 Jun 25 17:50 UTC | HN request time: 1.629s | source | bottom
Show context
simonw ◴[17 Jun 25 18:59 UTC] No.44302601[source]▶
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 published some notes on that article when it first came out: https://simonwillison.net/2024/Dec/20/building-effective-age...

A more recent article from Anthropic is https://www.anthropic.com/engineering/built-multi-agent-rese... - "How we built our multi-agent research system". I found this one fascinating, I wrote up a bunch of notes on it here: https://simonwillison.net/2025/Jun/14/multi-agent-research-s...

replies(5): >>44302676 #>>44303599 #>>44304356 #>>44305116 #>>44305898 #
1. koakuma-chan ◴[17 Jun 25 21:53 UTC] No.44304356[source]▶
Does anyone know which AI agent framework Anthropic uses? It doesn't seem like they ever released one of their own.
replies(2): >>44304965 #>>44305508 #
2. rockwotj ◴[17 Jun 25 23:04 UTC] No.44304965[source]▶
Just write the for loop to react to tool calls? It’s not very much code.
replies(1): >>44305510 #
3. ankit219 ◴[18 Jun 25 00:34 UTC] No.44305508[source]▶
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...

4. koakuma-chan ◴[18 Jun 25 00:35 UTC] No.44305510[source]▶
They mentioned hand offs, sub agents, concurrent tool calls, etc. You could write that yourself, but you would be inventing your own framework.
replies(2): >>44307411 #>>44307467 #
5. risyachka ◴[18 Jun 25 07:18 UTC] No.44307411{3}[source]▶
Its still just a loop.

Also - funny enough how “parallel calls” became a feature in AI? Like wow, yeah, we could call functions in parallel since the dawn of CS

6. crazylogger ◴[18 Jun 25 07:29 UTC] No.44307467{3}[source]▶
Sub-agent is another LLM loop that you simply import and provide as a tool to your orchestrator LLM. For example in Claude Code, sub-agent is a tool called "Task(<description>)" made available to the main LLM (the one that you chat with) along with other tools like patch_file and web_search.

Concurrent tool call is when LLM writes multiple tool calls instead of one, and you can program your app to execute those sequentially or concurrently. This is a trivial concept.

The "agent framework" layer here is so thin it might as well don't exist, and you can use Anthropic/OAI's sdk directly. I don't see a need for fancy graphs with circles here.

replies(1): >>44308812 #
7. koakuma-chan ◴[18 Jun 25 11:12 UTC] No.44308812{4}[source]▶
> The "agent framework" layer here is so thin it might as well don't exist

There's plenty of things that you need to make an AI agent that I woudn't want to re-implement or copy and paste each time. The most annoying being automatic conversation history summarization (e.g. I accidentally wasted $60 with the latest OpenAI realtime model, because the costs go up very quickly as the conversation history grows). And I'm sure we'll discover more things like that in the future.

replies(1): >>44308883 #
8. akadeb ◴[18 Jun 25 11:24 UTC] No.44308883{5}[source]▶
I would highly recommend gemini 2.5 pro too for their speech quality. It's priced lower and the quality is top notch on their API. I made an implementation here in case you're interested https://www.github.com/akdeb/ElatoAI but its on hardware so maybe not totally relevant
replies(1): >>44308949 #
9. koakuma-chan ◴[18 Jun 25 11:33 UTC] No.44308949{6}[source]▶
I'm using LiveKit, and I indeed have tested Gemini, but it appears to be broken or at least incompatible with OpenAI. Not sure if this is a Livekit issue or a Gemini issue. Anyway I decided to go back to just using LLM, SST and TTS as separate nodes, but I've also been looking into Deepgram Voice Agent API, but LiveKit doesn't support it (yet?).