Building Effective AI Agents

https://www.anthropic.com/engineering/building-effective-agents

by Anon84 • 1 year ago

543 88 1 year ago

spenczar5• 1 year ago

(December 2024, which somehow feels an eternity ago)

nahsra• 1 year ago

Yes, but it's held up really well in my opinion! I use this piece constantly as a reference and I don't feel it's aged. It reframed Anthropic as "the practical partner" in the development of AI tools.

nico• 1 year ago

Nooooo I'm going to have to use my brain again and write 100% of my code like a caveman from December 2024

https://news.ycombinator.com/item?id=44260988

simonw6• 1 year ago

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...

juddlyon• 1 year ago

Thank you for the extra notes, this is top of mind for me.

smoyer• 1 year ago

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

miki123211• 1 year ago

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.

XenophileJKO• 1 year ago

Having built several systems serving massive user bases with LLMs. I think the ability to swap out APIs just isn't the bottleneck.. like ever. It is always the behavioral issues or capability differences between models.

The frameworks just usually add more complexity, obscurity, and API misalignment.

Now the equation can change IF you are getting a lot of observability, experimentation, etc. I think we are just reaching that point of utility where it is a real question whether you should use the framework by default.

For example I build a first version of a product with my own java code hooking right into an API. I was able to deliver the product quickly with a clean architecture and observability, etc. Then once the internal ecosystem was aligned on a framework (on mentioned in the article) a team took up migrating it to python on the framework. It still isn't complete, it just introduces a lot of abstraction layers where you have to adapt them to your internal systems and your internal observability setup, and any other things that the rest of your applications do.

People underestimate that cost. So by default to get your V0 product off the ground (if you are not a complete startup), just use the API. That is my advice.

retinaros• 1 year ago

not only that it also ready you for production if the framework has constructs like observability, eval, deployment, cloud security , ect...

koakuma-chan4• 1 year ago

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

rockwotj• 1 year ago

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

ankit219• 1 year ago

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...

swyx• 1 year ago

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

kodablah3• 1 year ago

I believe the definition of workflows in this article is inaccurate. Workflows in modern engines do not take predefined code paths, and agents are effectively the same as workflows in these cases. The redefinition of workflows seems to be an attempt to differentiate, but for the most part an agent is nothing more than a workflow that is a loop that dynamically invokes things based on LLM responses. Modern workflow engines are very dynamic.

sothatsit• 1 year ago

I think the distinction is more about the "level of railroading".

Workflows have a lot more structure and rules about information and control flow. Agents, on the other hand, are often given a set of tools and a prompt. They are much more free-form.

For example, a workflow might define a fuzzy rule like "if customer issue is refund, go to refund flow," while an agent gets customer service tools and figures out how to handle each case on its own.

To me, this is a meaningful distinction to make. Workflows can be more predictable and reliable. Agents have more freedom and can tackle a greater breadth of tasks.

simonw6• 1 year ago

You appear to be making the mistake of assuming that the only valid definition for the term "workflow" is the definition used by software such as https://airflow.apache.org/

https://www.merriam-webster.com/dictionary/workflow thinks the word dates back to 1921.

There no reason Anthropic can't take that word and present their own alternative definition for it in the context of LLM tool usage, which is what they've done here.

gregorymichael• 1 year ago

One of my favorite AI How-tos in the last year. Barry and Erik spend 80% of the post saying ~”eh, you probably don’t need agents. Just build straightforward deterministic workflows with if-statements instead.”

And then, when you actually do need agents, don’t over complicate it!

This post also introduced the concept of an Augmented LLM — a LLM hooked up to tools, memory, data — which is a useful abstraction for evolving LLM use beyond fancy autocomplete.

“An augmented LLM running in a loop” is the best definition of an agent I’ve heard so far.

suyash• 1 year ago

I think the Agent hype has come down now

kevinventullo• 1 year ago

Now it’s all about AI Agencies

revskill• 1 year ago

So an agent is just a monoid in the category of monads ?

AvAn12• 1 year ago

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?

cmsparks• 1 year ago

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 actor style framework.

pyman2• 1 year ago

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

simonw6• 1 year ago

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 delegate to one or more sub-agents which might run in parallel. They use that trick for Claude Code - I have some notes on reverse-engineering that here https://simonwillison.net/2025/Jun/2/claude-trace/ - and expand on that in their write-up of how Claude Research works: https://simonwillison.net/2025/Jun/14/multi-agent-research-s...

It's still _very_ early in figuring out good patterns for LLM tool-use - the models only got really great at using tools in about the past 6 months, so there's plenty to be discovered about how best to orchestrate them.

svachalek• 1 year ago

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.

jsemrau2• 1 year ago

"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

gk1• 1 year ago

In at least the case for coding agents the emerging pattern is to have the agents use containers for isolating work and git for reviewing and merging that work neatly.

See for example the container use MCP which combines both: https://github.com/dagger/container-use

That’s for parallelizing coding work… I’m not sure about other kinds of work. I still see people using workflow builder tools like n8n, Zapier, and maybe CrewAI.

daxfohl4• 1 year ago

Nothing works automagically. You still have to build in all the operational characteristics that you would for any traditional system. It's deceptively easy to look at some AI agent demos and think "oh, I can replace my team's huge mess of spaghetti code with a few clever AI prompts!" And it may even work for the first couple use cases. But all that code is there for a reason, and eventually it'll have to be reckoned with. Once you get to the point where you're translating all that code directly into the AI prompt and hoping for no hallucinations, you know you've lost the plot.

whattheheckheck• 1 year ago

Then wtf is the point of this?

nurettin• 1 year ago

If I had to deal with "AI agent concurrency", I would get them to submit their requests to a queue and process those sequentially.

0x4572• 1 year ago

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.

rdedev• 1 year ago

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

deadbabe2• 1 year ago

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 LLM agent if the input is novel?

0x4572• 1 year ago

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

iLoveOncall• 1 year ago

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 start by using LLM APIs directly

Best advice of the whole article by far.

It's insane that people use whole frameworks to send what is essentially an array of strings to a webservice.

We've removed LangChain and LangGraph from our project at work because they are literally worthless, just adding complexity and making you write MORE code than if you didn't use them because you have to deal with their whole boilerplate.

fennecbutt• 1 year ago

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.

btbuildem• 1 year ago

use simple, composable patterns

It's somehow incredibly reassuring that the "do one thing and do it well" maxim has held up over decades. Composability ftw.

chaosprint• 1 year ago

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.

m3kw9• 1 year ago

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

EGreg• 1 year ago

What exactly makes them regress?

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

amelius• 1 year ago

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

jsemrau2• 1 year ago

(1) Running multiple agents is expensive, decreasing RoI. My DeepSearch agent for stocks uses 6 agents, and each query costs about 2 USD.

(2) Multi-agent orchestration is difficult to control.

(3) The more capable the model, the lower the need for multi-agents.

(4) The less capable the model, the higher the business case for narrow AI.

mellosouls• 1 year ago

Discussed at the time:

https://news.ycombinator.com/item?id=42470541

Building Effective "Agents", 763 points, 124 comments

NetRunnerSu• 1 year ago

The entire discussion around agent orchestration, whether centralized or multi-agent, seems to miss the long-term economic reality. We're debating architectural patterns, but the real question is who pays for the agent's continuous existence.

Today, it's about API calls and compute. Tomorrow, for any truly autonomous, long-lived agent, it will be about a continuous "existence tax" levied by the platform owner. The orchestrator isn't just a technical component; it's a landlord.

The alternative isn't a more complex framework. It's a permissionless execution layer—a digital wilderness where an agent's survival depends on its own resources, not a platform's benevolence. The debate isn't about efficiency; it's about sovereignty.

simonw6• 1 year ago

Which definition of "AI agent" are you talking about here? This sounds like some kind of replacement for a human in a position of authority?

sixhobbits• 1 year ago

this is just AI slop, what's the point of posting stuff like this here?

bredren• 1 year ago

It’s helpful but I think Anthropic should be offering non technical versions of this.

For example, a marketing group is interested in agents but needs a guide on how to spec them at a basic level.

There is a figure toward the end and an appendix that starts to drive at this.

Even though it’s new, “how to build them” is an implementation concern.

bgwalter• 1 year ago

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)?

ivape• 1 year ago

You are correct. Just about everyone trying to codify the patterns without at least giving it a few years is a doing everyone a disservice (looking at you Langchain).

evertedsphere• 1 year ago

in case someone from anthropic is reading this: could you please add a bit of padding on the outside of the page? at least on a phone screen, the text covers the entire width of the screen from edge to edge

Zaylan• 1 year ago

This article is a good reminder to start with the simplest thing that works and only add complexity when it's truly needed.

A few clearly defined LLM calls with some light glue logic usually lead to something more stable, easier to debug, and much cheaper to run. The flashy, full-featured agents often end up causing more problems than they solve.

guicen• 1 year ago

I like how this post avoids the hype and gets practical. Too often, people jump straight into building agent systems just because it's trendy, without asking if the task really needs it.

emeriezaiya• 1 year ago

I hope that AI is something that brings people help

suninsight3• 1 year ago

As someone who works for a company having a real Agent in production, (not a workflow), I cannot disagree more than the very first statement here: Use Agent Frameworks like Langraph. We did exactly that, and had to throw everything away just a month down the line. Then we built everything from scratch and now our system scales pretty well.

To be fair, I think there might be a space for using Agent Frameworks, but the Agent space is too early for a good enough framework to emerge. The semi contrarian though, which I hold to a certain extent, is that the Agent space is moving so fast that a good enough framework might NEVER emerge.

barrenko• 1 year ago

The event horizon of current AI space has been quite a thing to observe.

weego• 1 year ago

I'm just in the process of moving from a prototype in N8N's agent tools to an actual system that could be self-hosted.

I've read a lot of comments that most pragmatic shops have dumped langchain/graph, haystack, crew etc for their own internal code that does everything more simply, but I can't currently conceptualize how tooling etc is actually done in the real world.

Do you have any links or docs that you've used as a basis for the work you could share? Thanks.

suninsight3• 1 year ago

Most of our stuff is built in house actually, simply because everything else is still kind of catching up. You can find a bunch of information on the blog (https://www.nonbios.ai/blog)

The only software that we use is Langfuse for observability and that too was breaking down for us. But they launched a new version - V3 - which might still work out for us.

I would suggest to just use standard non-AI specific python libraries and build your own systems. If you are migrating from N8N to a self hosted system then you can actually use NonBioS to build it out for you directly. If you join our discord channels, we can get an engineer to help you out also.

gwd2• 1 year ago

It sounds like you're agreeing with the article? From TFA:

Over the past year, we've worked with dozens of teams building large language model (LLM) agents across industries. Consistently, the most successful implementations weren't using complex frameworks or specialized libraries. Instead, they were building with simple, composable patterns.
...There are many frameworks that make agentic systems easier to implement. ...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 start by using LLM APIs directly: many patterns can be implemented in a few lines of code.

i_love_retros2• 1 year ago

What job is the agent performing?

suninsight3• 1 year ago

It is AI Software Dev called NonBioS.ai

laurentiurad• 1 year ago

I used an n8n workflow I developed with one of the exact setups shown in the article. It costs me $3 and at least 3 minutes to get a response to a simple question. No thanks, I am sticking to normal search for the moment.

i_love_retros2• 1 year ago

Has anyone got an example of an agent doing work in production that is saving the company money and doing a genuinely worthwhile job (in other words it's not writing text that exists purely to fill space on a packet of chips)?

a_bonobo• 1 year ago

I like ChatIPT! It solves a real challenge with biodiversity data. It doesn't mention the term 'agentic' but there's definitely Python code being written and executed.

https://www.gbif.org/news/6aw2VFiEHYlqb48w86uKSf/chatipt-sys...

It's still in beta.

Press release:

Rukaya Johaadien's chatbot provides conversation-style support to students and researchers who hold biodiversity data but are first-time or infrequent data publishers. Its prompts guide users as it cleans and standardizes spreadsheets, creates basic metadata, and publishes well-structured datasets on GBIF.org as a Darwin Core Archive.

To date, publishing high quality data from PhD and Master's degrees and other small-scale biodiversity research studies has been difficult to do at scale. Standardizing data typically requires specialist knowledge of programming languages, data management techniques, and familiarity with specialist software.

Meanwhile, the process of gaining access to existing instances of the Integrated Publishing Toolkit (IPT)—the GBIF network's workhorse application for data sharing run by node staff with limited time and resources—can test a novice's patience. Training can do little to surmount such logistical barriers and others, like language, when occasional users forget the precise steps and details from year to year.

"Data standardization is hard, and biologists don't become biologists because they like coding or Excel, so a lot of potentially valuable data falls by the wayside," said Johaadien. "Recognizing that large language models have gotten really good at generating code and working with data, I built an automated tool to guide non-technical users through routine questions and process their messy data as much as possible, then publish it quickly and automatically to GBIF."

punkbit• 1 year ago

C'mon? There are plenty of 14yo founders on X-Twitter-TikTokers making 40K MRR doing that

lmeyerov• 1 year ago

For louie.ai, our users are doing agents and agentic reasoning for automating daily investigation work:

1. Agentic Automation: For every alert/ticket coming in, the agent does a pre-investigation across relevant APIs, DBs, etc, helping identify FPs and providing more context on real ones. Cuts down on human time and speeds up handling.

2. Vibes Investigation: The same agentic reasoning is used when spelunking, where beyond just text2sql, the LLM will spin 2-10 minutes to investigate Splunk, databricks, etc for you.

Underneath, the agent has tools like semantic layers over DBs, large logs/text/dataframe analysers, etc .

Building Effective AI Agents

Related Stories