🤯 Wow, this was so helpful and totally eye-opening from a non-developer perspective! I have a question for you: I've been watching so many UA-cam videos where people say they are building agents, but if I understand what you're sharing here, they are really just building workflows and calling them agents. Is that correct?
Yes and just to clarify it further. You can just use an LLM (with tools) in a workflow to do most of the things. You mostly dont' need an LLM to make autonomous decisions but rather use pre-defined workflows.
This is 100% true! I build a multi agent app on azure and it was too complex, the goal was to take a user request and use tools to perform analysis, the problem was that the requests we not always sent to the right agent, best to use a pre-defined / predictable paths.
Did you build an ai decision maker agent that acts as the initial layer to take in a request? It’s only training is how to make decisions on which tools to call.
@ yes, there were 4 total agents, the first layer was the decision layer that passed the request to the next agent based on the initial classification and data
@@harisjaved1379 what prompts were you using for the orchestrator. That’s where the magic happens. You can’t go budget with orchestrator. IMO you just need to use o1 and have a large pre-prompt with examples and directives in the chain of messages that are passed to the decision agent.
Same brother. I think this bigger companies may be intentionally trashing these frameworks…think Microsoft GitHub…I am realizing that everything seems to be a scam.
Which framework do you feel is best at the moment for building AI agentic solutions? I am learning langgraph which is descent, but I am hearing PydanticAI is great as well.
I totally agree with this assessment- after all we are just calling a very simple API when working with LLMs - no need to learn a framework to do that
🤯 Wow, this was so helpful and totally eye-opening from a non-developer perspective! I have a question for you: I've been watching so many UA-cam videos where people say they are building agents, but if I understand what you're sharing here, they are really just building workflows and calling them agents. Is that correct?
Yea these words are new and there is not a clear boundary around them yet.
thats partly correct. think of an agent as a worker that performs a task based on a workflow
Yes and just to clarify it further. You can just use an LLM (with tools) in a workflow to do most of the things. You mostly dont' need an LLM to make autonomous decisions but rather use pre-defined workflows.
Yes
@@engineerpromptexactly this, most people just want tools with their LLM. Agents are so buggy right now. Wait a year I'm sure they will be better.
This is 100% true! I build a multi agent app on azure and it was too complex, the goal was to take a user request and use tools to perform analysis, the problem was that the requests we not always sent to the right agent, best to use a pre-defined / predictable paths.
Did you build an ai decision maker agent that acts as the initial layer to take in a request? It’s only training is how to make decisions on which tools to call.
@ yes, there were 4 total agents, the first layer was the decision layer that passed the request to the next agent based on the initial classification and data
@@harisjaved1379 what prompts were you using for the orchestrator. That’s where the magic happens. You can’t go budget with orchestrator.
IMO you just need to use o1 and have a large pre-prompt with examples and directives in the chain of messages that are passed to the decision agent.
I have yet to find a prompt chaining framework that is not complete trash
Same brother. I think this bigger companies may be intentionally trashing these frameworks…think Microsoft GitHub…I am realizing that everything seems to be a scam.
Which framework do you feel is best at the moment for building AI agentic solutions?
I am learning langgraph which is descent, but I am hearing PydanticAI is great as well.
Tbh I've come to the conclusion that raw dogging it is simply the best option
Sucks to hear. What has failed so far, like what’s the actual problem?
Thank you so much! This was very clarifying.
I just did a live yesterday showing how to build powerful agents with no-code 🔥
What do you think of pydanticAI?
Its all in the prompts, and the use of prompt chains.
#PromptChainGang
Hey can you tell me which application u r using for that GUI demonstration?
if you are talking about my screen recorder? I use screen studio.
Beautiful
I built this system 11 months ago; I am ahead of RAgentic 😂 time.
LangGraph sucks unless you have a Mac I guess…
I hate agents