Awesome video! By the way, in general your format, pacing, conciseness and the cool but also utilitarian "code floating above your speaking" is a nice touch! I know making these videos takes a lot so just want to give kudos where it's clearly deserved! There's so many "faceless", auto-gen'd content or just click-baity low-content videos so this was a welcomed break from that!
I used CrewAI one or two times. It's simple but takes a lot of time, a lot of issues, a lot of tokens, and came to the same conclusion as yours! By the way, actually, after a lot of "improvements", it becames confusion instead of the simplicity of the beginning. Today I use light weight and straight forward automations!
loved seeing this Matt. I have spent far too much time trying to write code that fits into one agentic framework or another, whilst always feeling it should be the other way around. This is a real gem of a video and anyone that says you're an idiot, just hasn't used any of the available agent frameworks. The community was crying out for this video! Bravo sir.
This video inspired me to use xstate + ollama json/functions instead of langgraph or crewai. I have made so much more progress with my advanced AI agent workflows and learned quite a bit more about state and complex logic in the process. Thanks for this video.
I have to admit that I've had more success just using the OpenAI API than from my experiments with CrewAI, or AutoGen, where I often feel like I'm fighting the framework. Good video
Great video Matt! I fully agree with what you say. I've been on this track for a long time and have built a TS framework for it. I could not understand why all these agentic tools were so complex (and required agents to make obvious decisions which they sometimes failed at) and why everyone was hyping them so much (especially since you can make much more reliable tools in a simpler way). At the same time, I was unable to give words to why I felt this way. Your video helped me give words to why I felt this way! Thanks!
I love what you have been sharing on this channel. As a developer I really enjoy the content like in this video which is not just a tutorial on a tool but knowledge that is deeper. Also less code and more control, yes please !
You are spot on and shows the difference between "letting the ai do the work" vs "making a good, resource efficient, lean process". This is why softeare engineers will have jobs for a while- along with the issue of mission critical reliability and confidence.
I am using LangGraph which is also very deterministic. It uses a state and you can define functions as nodes (agents) thus for some tasks I avoid LLM which speeds up the process… The downside is of course that it takes some time to learn it. But if you do write a couple of them you can use them as templates for new projects. CrewAI is inconsistent and not useful for production at least in my case…
It makes a lot of sense. As someone who is only just getting started playing with local LLMs, something like CrewAI seems easiest. Maybe what we really need is some good tutorials for leveraging existing libraries and techniques like you did. Thank you for making this - looking forward to your next videos!
Tools like crew have amazing intentions but it still has a bit of work to do to become something useful. It’s already starting with a lot of baggage but hopefully with the money they raised they can get some of that solved and be something very cool. M
I used CrewAI for an internal prototype and my main issue is the framework has near zero observability. If I put crews into FastAPI async, guess what? They just fail without any notification at all. Plus the only RUclips video claiming to use FastAPI with crew that I could find seems fake. The guy doesn’t even show his code, probably because it didn’t actually work and he had to hardcode his app to get the video out. There’s a lot of money sloshing around for agentic AI and a lot of short cuts are being taken. In the last month Crew has rewritten its code base and examples multiple times. I think AI is helping as it’s quickly becoming a useless dumpster fire. I can’t use Crew in a real application. But it’s certainly great for RUclips videos and paid promotional marketing! 🎉 Thanks so so much for making this. You’ve made my life much easier by pointing out simpler examples.
Thank you, Matt. You're right. If the process is simple and known, no agent is needed. Agents are meant for harder problems, e.g. independently figuring out the process to achieve a goal.
It makes a lot of sense actually. If anyone is a programmer I’m sure one can use the logic and write functions to automate it. For normal humans, we can only try to come up and refine the prompt to do a task, then take that output and feed it to another agent and so on.
True... But trust me, take the time to learn. I'm still mad at myself for wasting two years from 1996 to 1998 with Microsoft Front Page when I could have just learned HTML in 3 months.
@@johngoad why would you be mad at Front Page? lol That was a good program back then. If you started doing web at that time those two years at least helped you with content structure.
Thank GOD! One person I can always trust. I was exactly searching for this. :) I really dint want to use any of the "decorators" that mascarade as a framework :P
I've used CrewAI pretty extensively. It is good for a specific type of agentic app, namely agents executing tightly structured processes in a coworking environment, but it is inflexible and rather buggy, especially if you're not using OpenAI's LLMs.
all frameworks are hype. the time it takes to learn their documentation/APIs is better spent implementing the custom solutions your project needs, and you won't be held back.
There’s a point to be made about using an opinionated framework when you have multiple developers of varying seniority and expertise in AI development. A framework can help make the dozens or hundreds of small AI tools a company develops a bit easier to manage. Sure, there’s boilerplate but at least the framework helps enforce certain structure and style. Of course, you could have your own style guides and internal docs demoing the 60 lines needed here and use code reviews as a way to make sure people comply the company’s rules so I don’t know how much of a difference a framework does in the simplest cases. I wonder if the tides turn when you need to have more stuff: persistent memory, observability/traceability etc. Developing these by yourself every time doesn’t make sense and once you start building reusable libraries for the tasks, you’re soon building your own framework (which is what you were trying to avoid in the first place).
So true Matt. I’ve been trying to achieve code research tasks using a RAG and Ollama with local models and CrewAI framework for about two months, with no good results so far. Where a simple chat with Ollama and feeding the chat with results from the same RAG gives way better results and consistency. I’m keeping the CrewAI program just for evaluating new updates and see if it’s improving over the time with same agents and prompts…
He reminds me of a anthropology teacher in high school that was super cool. He kept the subject matter interesting & focused. I like this channel. Well Done
Completely agree, before I start to learn Python, I just implement the things I really need with the language I already know. Agents is just an architectural pattern, you don't need a framework.
Function calling⁉️😂 there’s got to be a better name… I’ve built a few dozen personal projects in CrewAI and while I enjoy working with the framework, I agree it’s not the right tool for every agentic workflow. It is hard to debug currently. I really like your content, brings some fresh air into the space and the motion graphics are sick! 💯
Well, back in my day, I had to walk through 25 feet of snow to get to the nearest computer, which was the lady down the street, since computers were just people. Is that what your granddad would have said?
Spot on. Agent frameworks are good for chatbots that need to deal with a large range of tasks...but well defined workflows can just be LLM-based automations with a human in the loop
Thanks ... I appreciate you POV... I have used CrewAI, AutoGen and more.. I have wasted tons of time learning stuff that I don't use because at some point (usually 3/4 of the way in) I realize the limitations. I mostly just learn why it is not for me. Not sure if I can put a finger exactly on what it is, but it seems to me like most stuff is built these days with training wheels.
If i can suggest something for the ranking formula, use coefficients from geometric series. 1/2^n where n is the position of the term, this will create no overlaps between ranked videos in the ranking space. P.s. thank your for this video.
Great points about Kubernetes being overkill and just the over focus on Python etc. I am building an open source tool inspired by Laravel PHP just to help me see how it is not the language but so much more. And good points about automation, to me I want normal non coding users to see the power and ease of this as they see the power of prompts. Anyways great one!
I was fixated on using CrewAI and langchain for agent building. Thanks for sharing your perspective. It's more clear to me on when exactly to use these frameworks.
I've tried a few different ways of getting more complex tasks done. I like the simplicity of this one. It fits my experience in that I find unless I plan on use a framework a lot, it's easier to just program the task(s) in a straight forward manner rather than take the time to learn a new package. I recall learning to use a MVC package to manage a somewhat complex web site. It really took longer than if I had just written it from scratch. I work on my own and seldom need to share my code with anyone else. Not that I don't want to but it never seems to work out.
Love the awkward silence. As a not-coded-forever person, who roughly understands what you are doing vs crew AI…. I like your approach. Simpler is generally better and faster… BUT may not be an extensible in the future. Which may be irrelevant in this scenario.
While I agree with the sentiment that simpler is better. Sometimes you don't know that you could benefit from the ability to let the LLM talk back and forth between other LLMs until you've tried it on several workflows. If your plan is super well defined then it makes sense to simply the design, but for now I'll continue using crewai to scaffold out AI based workflows till I can determine the true limits of the models that are available. Good video though! Thank you for putting it together. It made me think!
Thanks for the video! I agree the frameworks are not ready yet; SuperAGI is another example. Very, very promising but not there yet. But most people just don't know how to code so the frameworks like CrewAI are simply the only choice. Maybe in a next video you could show how the results of a solution with coding are faring against CrewAI & co. Would give a perspective on the maturity status of these frameworks.
Yep, this was what I was thinking too. LangGraph, crewAI etc. are cool to get started and build your first agent, but they really have a lot of unnecessary components, and they're creating complicated abstractions over pretty simple components
Great one, and fully aligned with you. People are always focusing on the tool instead of focusing on the need. Most of the agentic framework I’ve seen so far were falling apart as soon as you’re trying to implement something a little bit complex … and rely and local models. And the one big problem they all have (but somehow your code as well) is that they are as good as your prompting skills are … which on top will vary depending on the model you use …
the prompting issue I think is valid. But still, we don't really know what works best yet, it's no man's land. I think that overtime you could try out different prompts and see how they perform, but obviously it takes time to collect this data.
I think it is a matter of using abstractions. If you just need to get things done - it is ok to use simple tools but when your prototype becomes more and more complicated you may need more abstractions in order to maintain all this stuff (if you use langchain for simple RAG - it will be easier to add extra LLM type support). I do like crew and langgraph because it is easier to maintain pipelines when you need to check agent’s results automatically, to make some decisions based on that or to have cycles. I prefer to use LangChain even just for simple LLM calls because it is easier to switch to another LLM and not to deal with issues like “Claude has system prompt as another parameter instead of first chat message” etc
Why do you think there are a good number of codebases going to GO over Python? I noticed Fabric Framework did this a little while ago. Also, love your videos subscribed for sure.
Packaging is a huge one. Distributing any product that requires Python means a lot of support issues. And Python tends to be slower. I’m not sure I see a reason any package would choose to start with Python. There really isn’t any benefit.
@@technovangelist, thank you for the response! As a full-stack developer, I always use Python on the backend, and I would love to learn Go and give it a shot for upcoming projects. I've used Python for so long that I never learned Go. I would like to try it out and see how the performance and code differ. I just found your channel yesterday and love it.
Wish there was a channel like this for those of us who don't code but want to get the same things out of AI, which. is really where AI should be going. We shouldn't care of it's Python, Go, Rust etc. We should just describe what we want and the finished product, with some iterations, should pop out the other end.
Matt, new to agentic flows I’ll admit, but I was wondering if a n8n workflow could be the “right tool for the job” (where the flow can be defined)? 4:34
anyway, my idea of a good agent framework would include this: in a userfriendly webinterface i can write down the request to find a good solution for an idea or project and the agent framework would come up with the choice of the appropriated agents and they identify all the tasks they need to get done to achieve the goal.
You put on the table a hot topic. All frameworks that I have seen until know and their documentation and their architecture as ano mature framework. Their launch their framework just to be the first on the marker but documentation is weak, outdated and even worse that clases are too many and confuse. I have my own bot running wirh N8n JS MySql and running non trivial uses cases. I think this agentic AI will be an standard but frameworks has to mature a little one. I used langchain, langgraph, llamaindex, phidata and phidata l seems to be easiest for most trivial uses cases. Programmer spend too much time reading and trying to understand classes and is hard
I made a few rag thing in crewai, and while I love it, there's some huge gaps. Like you mentioned, when you know a tool, just tell it to use a tool. I find it cumbersome not to be able to properly debug prompts without using agentops or something. I do actually like the agents vs tasks vs tools solution, but in practice, the agent almost becomes an LLM connection rather than it's own thing.
Great perspective and food for thought. Having arranged / organized some openai and groq api calling with aws step functions, I really wondered why I needed to let the orchestration agent in any of these new fangled frameworks do anything (obvious).
Great breakdown of simplifying AI workflows! Have you explored frameworks like KaibanJS? Its Kanban-style approach offers a clean way to visualize and manage multi-agent systems efficiently
I remember that Charles Petzold book . . . learned a lot from that. He's a cool guy. You should check out his book on Turing or his book on Code. Neat guy.
Your content is always so good. You explain things really well, and your editing (code overlays, text graphics, etc.) make these so fun to watch. Keep up the great work!
Tools/function calling is the proper way to do this but it becomes expensive very quickly because of the additional tokens used on every call. The frontier providers are all currently workng on tackling this and hope tools is in scope. Autogen is probably the most developed tool right now but I've found it to be problematic as the AI's can get stuck in loops !
Thanks Matt, I can't get it to run, but thanks. I guess you're using linux, and I am on windows. I am not a programer and all the stuff I have used works with node.js not bun? Not sure what bun or bun.js is, I tried and could not get this to run. But thanks for taking the time to share.
Very interesting. You brought up a really good point. I was actually wondering why I never really got into CrewAi, and the simple answer is that it was never really useful. Reliability and using as few tokens as possible are important. Actually you want to use LLMs as little as possible
you're right, but your approach require a deeper knoledge of programming, and all that tools are moving on the hopposite direction. As you told, the right tool depend of the thing you're doing, but I think the more complex the thing will be, less advantage your solution will get. last but not least, business side, people that know that tools ( CrewAI and the others) will have a vantage.
The way I see it, with this workflow, is feels like you're actually creating something, and that you know every piece of the puzzle. As opposed to relying on some framework's internal workings, of which you have to spend time learning and adapting your way of reasoning to that of the authors'. Of course, your point still stands. This is only valid for programmers, not normal users.
Crew and the others are dev tools. My approach requires less knowledge and gets it done. Those other tools simply complicate things while adding nothing of value.
Coding is a pretty basic skill anyone can learn. Not much different from speaking a language. That said there are plenty of ways to do this stuff without coding too
This video is absolutely on spot - I was thinking exactly the same: why do I need to install a framework just to few functions. You did it so well so I am even surprised! Btw, the new visual elements on your video are great, but a bit distracting and rough... Yet I like them ... but I personally would prefer them a bit more refined in size, contrast and position. Keep in mind I watch on 2x speed, so maybe they are fine :D (Now it is like an over-salted dish... somehow less salt would make it perfect for my taste :) )
Hi Matt, good video here. I like your idea of keeping things simple. I just don't understnad the formula you show at 6:50. So is the score=(likes*comments*24e-3)/(subs*views*days)? Maybe some of multiplications are sums?
6:40 I'm confused about this equation. Score = (Views/Subs)*.4 * (Likes/Views)*.3 * (Comments/Views) * .2 * (1/DaysSincePub) The constants can be multiplied together, and two of the Views cancel out. So I think you end up with: Score = 0.024 * (Likes * Comments) / (Subs * Views * DaysSincePub) Is there any particular reason it was formatted the way shown at 6:40? "The views are more important than the likes, and the likes are more important than comments." I'm not sure if the formula is capturing what the wording here implies. Since Views ends up in the denominator, views actually end up a bad thing. Higher views = lower Score. Is that intended...? Edit: OK, nevermind. Looks like at 9:10, these values are added, and not multiplied. Which means they don't cancel out. So I guess it's fine :)
First I cant call you an idiot. I agree with you about the wrong tool. I am a typescript first dev but I have been using python just because the agent framework runs python. It delayed my development by a to with a lot of confusion because now I also have a task of brushing my python. Thank you very much for the clarity.
I think similar. But to be honest I haven't tried those frameworks. From what I saw they seem to be too complex for most of the tasks you will need an agent. Most of the time - my point of view - you just need a specialized agent/workflow and not an agent who "can" do everything. Otherwise it would get to complicated as Matt is emphasizing here. I was discovering "instructor", a python library for getting structured output from LLMs in JSON using OpenAIs client and for a bunch of other providers. Since a few days there is a new library called "ollama-instructor" with the same approach but using Ollamas python client natively. Both use Pydantic for creating and validating the JSON response from the LLM. Opinion: With "instructor" or "ollama-instructor" you can create specialized workflows where you have more control over the flow itself and the outcome as with an agent framework.
At 6:50 for the formula, I think the polynomial needs "+" (instead of the "x") after the numerics so you have separate terms. Oh actually at 9:12 looks like you get 'em, okay now..
![I.N "HALLUCINATION" | [Stray Kids : SKZ-PLAYER]](http://i.ytimg.com/vi/n5B5q1Hwt_U/mqdefault.jpg)
Awesome video! By the way, in general your format, pacing, conciseness and the cool but also utilitarian "code floating above your speaking" is a nice touch! I know making these videos takes a lot so just want to give kudos where it's clearly deserved! There's so many "faceless", auto-gen'd content or just click-baity low-content videos so this was a welcomed break from that!
I used CrewAI one or two times. It's simple but takes a lot of time, a lot of issues, a lot of tokens, and came to the same conclusion as yours! By the way, actually, after a lot of "improvements", it becames confusion instead of the simplicity of the beginning. Today I use light weight and straight forward automations!
use openrouter to use cheap models
You are spot on, Matt. CrewAI reflects all the new tools in the AI space in general: too much hype, not enough utility... yet.
loved seeing this Matt. I have spent far too much time trying to write code that fits into one agentic framework or another, whilst always feeling it should be the other way around. This is a real gem of a video and anyone that says you're an idiot, just hasn't used any of the available agent frameworks. The community was crying out for this video! Bravo sir.
You're the best man! No one does anything as exciting as you do, with simplicity and exact methodology!
This video inspired me to use xstate + ollama json/functions instead of langgraph or crewai. I have made so much more progress with my advanced AI agent workflows and learned quite a bit more about state and complex logic in the process. Thanks for this video.
Simplicity is the product of wisdom, and that comes from effective experience. Most excellent video.
I have to admit that I've had more success just using the OpenAI API than from my experiments with CrewAI, or AutoGen, where I often feel like I'm fighting the framework.
Good video
Thanks for stopping by.
It is true for now... but then you have to pay and it is not private.
This is what we need. Crewai... too much hype and not enough utility. Thanks for sharing.
I think a BPMN 2.0 tool with service task is enough instead of a dedicated agent framework.
Great video Matt! I fully agree with what you say. I've been on this track for a long time and have built a TS framework for it. I could not understand why all these agentic tools were so complex (and required agents to make obvious decisions which they sometimes failed at) and why everyone was hyping them so much (especially since you can make much more reliable tools in a simpler way). At the same time, I was unable to give words to why I felt this way. Your video helped me give words to why I felt this way! Thanks!
I was just sooo impressed when you mentioned "state machines", when properly used, they are awesome! 👌
I love this. Exactly. Spot on. This is why I'm building my new project from scratch.
I love what you have been sharing on this channel. As a developer I really enjoy the content like in this video which is not just a tutorial on a tool but knowledge that is deeper. Also less code and more control, yes please !
Thanks for the comment and for being a member
I have yet to make a choice and commit to a framework. Glad I watched this video first.
You are spot on and shows the difference between "letting the ai do the work" vs "making a good, resource efficient, lean process". This is why softeare engineers will have jobs for a while- along with the issue of mission critical reliability and confidence.
AI will slowly take jobs, but more senior devs are pretty safe for a while.
I am using LangGraph which is also very deterministic. It uses a state and you can define functions as nodes (agents) thus for some tasks I avoid LLM which speeds up the process… The downside is of course that it takes some time to learn it. But if you do write a couple of them you can use them as templates for new projects. CrewAI is inconsistent and not useful for production at least in my case…
Did you use langchain 2.0?
You could also just get flowise and then everything can be done with a gui. It just uses nodes which means you dont need to look through the code.
@@pin65371 Flowise has the customizability to build an agency? I've been trying to decide which Framework
@@pin65371 cool I am using LangGraph too, but I thought I would love a gui flow, thanks❤️❤️❤️
Flowise's UI is buggy at the moment. Also they lack documentation.
It makes a lot of sense. As someone who is only just getting started playing with local LLMs, something like CrewAI seems easiest. Maybe what we really need is some good tutorials for leveraging existing libraries and techniques like you did.
Thank you for making this - looking forward to your next videos!
Tools like crew have amazing intentions but it still has a bit of work to do to become something useful. It’s already starting with a lot of baggage but hopefully with the money they raised they can get some of that solved and be something very cool. M
I used CrewAI for an internal prototype and my main issue is the framework has near zero observability. If I put crews into FastAPI async, guess what? They just fail without any notification at all. Plus the only RUclips video claiming to use FastAPI with crew that I could find seems fake. The guy doesn’t even show his code, probably because it didn’t actually work and he had to hardcode his app to get the video out.
There’s a lot of money sloshing around for agentic AI and a lot of short cuts are being taken. In the last month Crew has rewritten its code base and examples multiple times. I think AI is helping as it’s quickly becoming a useless dumpster fire. I can’t use Crew in a real application. But it’s certainly great for RUclips videos and paid promotional marketing! 🎉
Thanks so so much for making this. You’ve made my life much easier by pointing out simpler examples.
Excellent material Matt! thank you. I am delighted to watch your presentations. This is my favorite channel.
well crew helps me scale, certainly initially it was annoying to setup, but then i just spin up new crews in 5mn whenever i need a new feature!
Thank you, Matt. You're right. If the process is simple and known, no agent is needed. Agents are meant for harder problems, e.g. independently figuring out the process to achieve a goal.
Agents are no more than a prompt. Sometimes a loop. But crew and similar tools are just a gimmick.
@@technovangelist haha....well said
It makes a lot of sense actually. If anyone is a programmer I’m sure one can use the logic and write functions to automate it. For normal humans, we can only try to come up and refine the prompt to do a task, then take that output and feed it to another agent and so on.
True... But trust me, take the time to learn. I'm still mad at myself for wasting two years from 1996 to 1998 with Microsoft Front Page when I could have just learned HTML in 3 months.
@@johngoad why would you be mad at Front Page? lol That was a good program back then. If you started doing web at that time those two years at least helped you with content structure.
@@vitalis Back then, production level code required hand written HTML.... My company had 20 writing HTML and 5 programmers. True story...
Thank GOD! One person I can always trust. I was exactly searching for this. :) I really dint want to use any of the "decorators" that mascarade as a framework :P
I’m marking any emails I get with the word “delve” in them as spam 😂
Genius! 😆
I've used CrewAI pretty extensively. It is good for a specific type of agentic app, namely agents executing tightly structured processes in a coworking environment, but it is inflexible and rather buggy, especially if you're not using OpenAI's LLMs.
I absolutely love Matts Videos, such a cool person, and keeps things simple.
all frameworks are hype. the time it takes to learn their documentation/APIs is better spent implementing the custom solutions your project needs, and you won't be held back.
Wise
@@petemoss3160 exactly
There’s a point to be made about using an opinionated framework when you have multiple developers of varying seniority and expertise in AI development. A framework can help make the dozens or hundreds of small AI tools a company develops a bit easier to manage. Sure, there’s boilerplate but at least the framework helps enforce certain structure and style. Of course, you could have your own style guides and internal docs demoing the 60 lines needed here and use code reviews as a way to make sure people comply the company’s rules so I don’t know how much of a difference a framework does in the simplest cases.
I wonder if the tides turn when you need to have more stuff: persistent memory, observability/traceability etc. Developing these by yourself every time doesn’t make sense and once you start building reusable libraries for the tasks, you’re soon building your own framework (which is what you were trying to avoid in the first place).
This is the most sane thing I've seen about Crew AI. Thank you.
your welcome
I am just getting started on learning about agents. So glad to find this video and hear your perspective.
Glad to be of help
So true Matt. I’ve been trying to achieve code research tasks using a RAG and Ollama with local models and CrewAI framework for about two months, with no good results so far. Where a simple chat with Ollama and feeding the chat with results from the same RAG gives way better results and consistency. I’m keeping the CrewAI program just for evaluating new updates and see if it’s improving over the time with same agents and prompts…
He reminds me of a anthropology teacher in high school that was super cool. He kept the subject matter interesting & focused.
I like this channel. Well Done
Completely agree, before I start to learn Python, I just implement the things I really need with the language I already know.
Agents is just an architectural pattern, you don't need a framework.
Spot on. Amazing how clear you explain things. love this channel. kudos
Function calling⁉️😂 there’s got to be a better name…
I’ve built a few dozen personal projects in CrewAI and while I enjoy working with the framework, I agree it’s not the right tool for every agentic workflow. It is hard to debug currently.
I really like your content, brings some fresh air into the space and the motion graphics are sick! 💯
the silence part is so cool!
Outstanding video. As a complete newbie this was intriguing, well explained and engaging.
New subber and bell set
Great video, efficient and effective.
I love his videos. It feels like my grandad is telling me calming stories. I mean it in the gooodest way 😄
Well, back in my day, I had to walk through 25 feet of snow to get to the nearest computer, which was the lady down the street, since computers were just people. Is that what your granddad would have said?
Finally, someone making sense :) I would never use crewai it's just hard work and in production its gives more problems than it solves.
Love the pragmatic approach, thank you for the video. Rethinking my LlamaIndex learning now.
Your “awkward pauses” at the end remind me so much of Craig Ferguson’s late night shows.
Spot on. Agent frameworks are good for chatbots that need to deal with a large range of tasks...but well defined workflows can just be LLM-based automations with a human in the loop
Yep. And in most cases, if you think there isn't a well-defined workflow, it just means you haven't really thought about it, and there probably is.
Your videos are always a great reality check. Thank you so much, Matt.
Glad you like them!
Thanks ... I appreciate you POV... I have used CrewAI, AutoGen and more.. I have wasted tons of time learning stuff that I don't use because at some point (usually 3/4 of the way in) I realize the limitations. I mostly just learn why it is not for me.
Not sure if I can put a finger exactly on what it is, but it seems to me like most stuff is built these days with training wheels.
When Matt talks.. I listen! Spot-on dear Sir
Thank you so much for this video. Super helpful and well-presented. Your time and effort is most appreciated!
My wife told me not to bother with these brand new frameworks (LangChain, CrewAI, Semantic Kernal, Amazon Q). Make my own. She was right.
Your wife sounds awesome.
By definition, the wife is ALWAYS right. So . . .
True
If i can suggest something for the ranking formula, use coefficients from geometric series. 1/2^n where n is the position of the term, this will create no overlaps between ranked videos in the ranking space.
P.s. thank your for this video.
Great Stuff! totally agree, crewai main idea behind is a - HYPE, not code, not devs, not user experience. so good to know i’m not alone here 🙌😀
Great points about Kubernetes being overkill and just the over focus on Python etc.
I am building an open source tool inspired by Laravel PHP just to help me see how it is not the language but so much more.
And good points about automation, to me I want normal non coding users to see the power and ease of this as they see the power of prompts.
Anyways great one!
I was fixated on using CrewAI and langchain for agent building. Thanks for sharing your perspective. It's more clear to me on when exactly to use these frameworks.
Great timing. I was just about to dive into some of these, but I'm not a Python guy and I like your approach better. Good points re: utility. Thanks!
Amazing video, man!
moving your head Up and Down to stop your camera?! Wow, Great job man that is a pure epic script^^
Huh?
@@technovangelist now you got to do it for real lol - The People have spoken
what does this mean?
I've tried a few different ways of getting more complex tasks done. I like the simplicity of this one. It fits my experience in that I find unless I plan on use a framework a lot, it's easier to just program the task(s) in a straight forward manner rather than take the time to learn a new package. I recall learning to use a MVC package to manage a somewhat complex web site. It really took longer than if I had just written it from scratch. I work on my own and seldom need to share my code with anyone else. Not that I don't want to but it never seems to work out.
Love the awkward silence.
As a not-coded-forever person, who roughly understands what you are doing vs crew AI…. I like your approach. Simpler is generally better and faster… BUT may not be an extensible in the future. Which may be irrelevant in this scenario.
Awesome, thoughtful video, Matt! And you have an amazing voice--you should license it to ElevenLabs. 😁
as always, love it! good job man !
While I agree with the sentiment that simpler is better. Sometimes you don't know that you could benefit from the ability to let the LLM talk back and forth between other LLMs until you've tried it on several workflows. If your plan is super well defined then it makes sense to simply the design, but for now I'll continue using crewai to scaffold out AI based workflows till I can determine the true limits of the models that are available. Good video though! Thank you for putting it together. It made me think!
but you don't need crew to add that. crew adds nothing and just complicates
Thanks for the video! I agree the frameworks are not ready yet; SuperAGI is another example. Very, very promising but not there yet.
But most people just don't know how to code so the frameworks like CrewAI are simply the only choice.
Maybe in a next video you could show how the results of a solution with coding are faring against CrewAI & co.
Would give a perspective on the maturity status of these frameworks.
Folks that don’t know how to code can’t use crew either
Very well illustrated! Thanks Matt
your welcome. thanks for stopping by
Loved with your idea
This is exactly why I switched to Yacana! CrewAI was a mess and wasn't able to call my functions. And also too much boiler plate code like you said.
Yes, please share your code for this and other practical use cases.
Thanks , your video make me think a lot, in my case I just need litellm and do the stuff by myself like you did, thanks again for opening my mind
You mentioned Charles Petzold, when i first read it i was 18. A lot of time has passed.
Yep, this was what I was thinking too.
LangGraph, crewAI etc. are cool to get started and build your first agent, but they really have a lot of unnecessary components, and they're creating complicated abstractions over pretty simple components
Great one, and fully aligned with you. People are always focusing on the tool instead of focusing on the need. Most of the agentic framework I’ve seen so far were falling apart as soon as you’re trying to implement something a little bit complex … and rely and local models. And the one big problem they all have (but somehow your code as well) is that they are as good as your prompting skills are … which on top will vary depending on the model you use …
the prompting issue I think is valid. But still, we don't really know what works best yet, it's no man's land.
I think that overtime you could try out different prompts and see how they perform, but obviously it takes time to collect this data.
Relying on local models is bad? Better give all your stuff to openai, you're right
I think it is a matter of using abstractions. If you just need to get things done - it is ok to use simple tools but when your prototype becomes more and more complicated you may need more abstractions in order to maintain all this stuff (if you use langchain for simple RAG - it will be easier to add extra LLM type support).
I do like crew and langgraph because it is easier to maintain pipelines when you need to check agent’s results automatically, to make some decisions based on that or to have cycles.
I prefer to use LangChain even just for simple LLM calls because it is easier to switch to another LLM and not to deal with issues like “Claude has system prompt as another parameter instead of first chat message” etc
As the project gets more complicated it’s even more important to keep it maintainable and get rid of these tools that complicate things like crew.
Wonderful content Matt. I might tweak it a little and use it for tiktok... and btw that score system OMG what a good idea!
Why do you think there are a good number of codebases going to GO over Python? I noticed Fabric Framework did this a little while ago. Also, love your videos subscribed for sure.
Packaging is a huge one. Distributing any product that requires Python means a lot of support issues. And Python tends to be slower. I’m not sure I see a reason any package would choose to start with Python. There really isn’t any benefit.
@@technovangelist, thank you for the response! As a full-stack developer, I always use Python on the backend, and I would love to learn Go and give it a shot for upcoming projects. I've used Python for so long that I never learned Go. I would like to try it out and see how the performance and code differ. I just found your channel yesterday and love it.
Wish there was a channel like this for those of us who don't code but want to get the same things out of AI, which. is really where AI should be going. We shouldn't care of it's Python, Go, Rust etc. We should just describe what we want and the finished product, with some iterations, should pop out the other end.
That’s probably a few months to a year out
Try Flowise, it is not perfect but can help get you going.
"Right, I don't code, but I want to be able to do the same as people who can code do, nevermind learning to code, that's for nerds."
Matt, new to agentic flows I’ll admit, but I was wondering if a n8n workflow could be the “right tool for the job” (where the flow can be defined)? 4:34
anyway, my idea of a good agent framework would include this: in a userfriendly webinterface i can write down the request to find a good solution for an idea or project and the agent framework would come up with the choice of the appropriated agents and they identify all the tasks they need to get done to achieve the goal.
Thanks for the video ❤
You put on the table a hot topic. All frameworks that I have seen until know and their documentation and their architecture as ano mature framework. Their launch their framework just to be the first on the marker but documentation is weak, outdated and even worse that clases are too many and confuse. I have my own bot running wirh N8n JS MySql and running non trivial uses cases. I think this agentic AI will be an standard but frameworks has to mature a little one. I used langchain, langgraph, llamaindex, phidata and phidata l seems to be easiest for most trivial uses cases. Programmer spend too much time reading and trying to understand classes and is hard
I made a few rag thing in crewai, and while I love it, there's some huge gaps. Like you mentioned, when you know a tool, just tell it to use a tool. I find it cumbersome not to be able to properly debug prompts without using agentops or something. I do actually like the agents vs tasks vs tools solution, but in practice, the agent almost becomes an LLM connection rather than it's own thing.
Great perspective and food for thought. Having arranged / organized some openai and groq api calling with aws step functions, I really wondered why I needed to let the orchestration agent in any of these new fangled frameworks do anything (obvious).
Thanks for sharing Matt great content!
Great breakdown of simplifying AI workflows! Have you explored frameworks like KaibanJS? Its Kanban-style approach offers a clean way to visualize and manage multi-agent systems efficiently
I remember that Charles Petzold book . . . learned a lot from that. He's a cool guy. You should check out his book on Turing or his book on Code. Neat guy.
Code is great
though i seem to remember there is a newer edition I haven't looked at
Pragmatism, I love it. Great channel! Thanks for sharing knowledge.
you really make sense , thanks
Your content is always so good. You explain things really well, and your editing (code overlays, text graphics, etc.) make these so fun to watch. Keep up the great work!
Thanks for the comment. I really do enjoy making them, and it's been fun adding new things every single time.
Can you talk about how you deploy this agent to run it periodically in the cloud?
I think supabase edge functions with supabase cron will be easy here
Tools/function calling is the proper way to do this but it becomes expensive very quickly because of the additional tokens used on every call.
The frontier providers are all currently workng on tackling this and hope tools is in scope.
Autogen is probably the most developed tool right now but I've found it to be problematic as the AI's can get stuck in loops !
There are no additional tokens used for function calling in ollama. Not sure what you mean. And there is no cost beyond you machine and gpu.
Apologies I'm referring to running hosted models operating at scale as opposed to running models locally.
Thanks Matt, I can't get it to run, but thanks. I guess you're using linux, and I am on windows. I am not a programer and all the stuff I have used works with node.js not bun? Not sure what bun or bun.js is, I tried and could not get this to run. But thanks for taking the time to share.
Very interesting. You brought up a really good point. I was actually wondering why I never really got into CrewAi, and the simple answer is that it was never really useful. Reliability and using as few tokens as possible are important. Actually you want to use LLMs as little as possible
I think it will mature and become a really great framework, but it's got some growing up to do.
Even better to not use any LLM at all, problem solved!
Excellent. Been wondering exactly this.
Looking forward for a video on your final process
you're right, but your approach require a deeper knoledge of programming, and all that tools are moving on the hopposite direction. As you told, the right tool depend of the thing you're doing, but I think the more complex the thing will be, less advantage your solution will get. last but not least, business side, people that know that tools ( CrewAI and the others) will have a vantage.
The way I see it, with this workflow, is feels like you're actually creating something, and that you know every piece of the puzzle. As opposed to relying on some framework's internal workings, of which you have to spend time learning and adapting your way of reasoning to that of the authors'. Of course, your point still stands. This is only valid for programmers, not normal users.
Crew and the others are dev tools. My approach requires less knowledge and gets it done. Those other tools simply complicate things while adding nothing of value.
@@technovangelist Is there a way non-devs can get their processes automated without having to learn coding?
Coding is a pretty basic skill anyone can learn. Not much different from speaking a language. That said there are plenty of ways to do this stuff without coding too
This video is absolutely on spot - I was thinking exactly the same: why do I need to install a framework just to few functions.
You did it so well so I am even surprised!
Btw, the new visual elements on your video are great, but a bit distracting and rough... Yet I like them ... but I personally would prefer them a bit more refined in size, contrast and position. Keep in mind I watch on 2x speed, so maybe they are fine :D
(Now it is like an over-salted dish... somehow less salt would make it perfect for my taste :) )
Hi Matt, good video here. I like your idea of keeping things simple. I just don't understnad the formula you show at 6:50. So is the score=(likes*comments*24e-3)/(subs*views*days)? Maybe some of multiplications are sums?
6:40 I'm confused about this equation.
Score = (Views/Subs)*.4 * (Likes/Views)*.3 * (Comments/Views) * .2 * (1/DaysSincePub)
The constants can be multiplied together, and two of the Views cancel out.
So I think you end up with:
Score = 0.024 * (Likes * Comments) / (Subs * Views * DaysSincePub)
Is there any particular reason it was formatted the way shown at 6:40?
"The views are more important than the likes, and the likes are more important than comments."
I'm not sure if the formula is capturing what the wording here implies.
Since Views ends up in the denominator, views actually end up a bad thing. Higher views = lower Score.
Is that intended...?
Edit: OK, nevermind. Looks like at 9:10, these values are added, and not multiplied. Which means they don't cancel out. So I guess it's fine :)
Thank you, I will be using your code for my YT videos!
First I cant call you an idiot. I agree with you about the wrong tool. I am a typescript first dev but I have been using python just because the agent framework runs python. It delayed my development by a to with a lot of confusion because now I also have a task of brushing my python. Thank you very much for the clarity.
You nailed it! 🎉
I think similar. But to be honest I haven't tried those frameworks. From what I saw they seem to be too complex for most of the tasks you will need an agent. Most of the time - my point of view - you just need a specialized agent/workflow and not an agent who "can" do everything. Otherwise it would get to complicated as Matt is emphasizing here.
I was discovering "instructor", a python library for getting structured output from LLMs in JSON using OpenAIs client and for a bunch of other providers. Since a few days there is a new library called "ollama-instructor" with the same approach but using Ollamas python client natively. Both use Pydantic for creating and validating the JSON response from the LLM.
Opinion: With "instructor" or "ollama-instructor" you can create specialized workflows where you have more control over the flow itself and the outcome as with an agent framework.
Did he cover he to pick the best “tool” for the job?
At 6:50 for the formula, I think the polynomial needs "+" (instead of the "x") after the numerics so you have separate terms. Oh actually at 9:12 looks like you get 'em, okay now..