What is Agentic AI? Important For GEN AI In 2025
Resumo
TLDRIn this video, Krish Naak discusses the advancements in generative AI and introduces the concept of agentic AI. Agentic AI represents autonomous systems that aim to achieve specific objectives without human oversight, contrasting it with generative AI, which primarily focuses on content generation. The video covers various frameworks like Lang Chain, F Data, and Microsoft Autogen that facilitate the development of agentic AI applications. Multiple examples illustrate the functionality of agentic AI, particularly in finance, showcasing its ability to perform complex tasks and provide data-driven recommendations.
Conclusões
- 🚀 Agentic AI is an evolution of generative AI, focusing on autonomous task execution.
- 🤖 It allows for complex workflows without human intervention.
- 🔧 Frameworks like F Data and Lang Chain are key tools for building agentic AI apps.
- 📈 Agentic AI has significant applications in finance, addressing market queries.
- 🎯 The goal of agentic AI is to deliver specific business outcomes.
- 💡 Understanding the differences between generative and agentic AI is crucial for developers.
Linha do tempo
- 00:00:00 - 00:05:00
Introduction to the channel and a summary of 2024, focusing on advancements in generative AI and the rise of large language models (LLMs). Discussion about the emergence of Agentic AI and the intention to elaborate on its capabilities and frameworks in the video.
- 00:05:00 - 00:10:00
Explanation of the differences between generative AI and agentic AI; while generative AI focuses on content creation through user queries and prompts, Agentic AI systems operate autonomously, working toward specific goals without requiring constant human input. Emphasis on integrating multiple tools to enhance functionality.
- 00:10:00 - 00:15:00
Introduction to practical examples and illustrations of agentic AI applications, emphasizing the complex workflows that can be generated to accomplish tasks like financial decision-making. A clear distinction between how agentic AI can autonomously manage various agents compared to generative AI.
- 00:15:00 - 00:22:35
Insight into various frameworks available for developing agentic AI applications, such as F data, Microsoft Autogen, and Langflow, and a demonstration of creating an end-to-end agentic AI application that interacts with external sources like stock market APIs to provide financial recommendations.
Mapa mental
Vídeo de perguntas e respostas
What is agentic AI?
Agentic AI refers to autonomous AI systems that can perform tasks independently to achieve specific goals.
How does agentic AI differ from generative AI?
Generative AI focuses on creating content, while agentic AI can operate workflows autonomously to meet defined business outcomes.
What frameworks are useful for developing agentic AI applications?
Frameworks like F Data, Microsoft Autogen, and Lang Chain are effective for building agentic AI applications.
Can agentic AI integrate with external tools?
Yes, agentic AI can integrate with various external tools and APIs to enhance its capabilities.
What examples of agentic AI applications are discussed?
Examples include financial analysis applications that compare stock performance and suggest optimal investments.
What role do LLM models play in agentic AI?
LLM models are often integrated into agentic AI systems to process and analyze data from various sources.
Ver mais resumos de vídeos
Sonic's Bath! - Sonic and Friends
The Awakening of White Apathy! 👁️ Mystic Flour Cookie 🌫️
ICT Forex - Accumulation - Manipulation - Distribution
Art of the Western World: #6 An Age of Reason, an Age of Passion
Spong Iron Production//DRI Production// #ironmaking
What actually causes high cholesterol? - Hei Man Chan
- 00:00:00hello all my name is Krish naak and
- 00:00:02welcome to my YouTube channel so guys as
- 00:00:05you all know that we are towards the end
- 00:00:07of 2024 uh there are some few more days
- 00:00:10to probably uh you know complete 2024
- 00:00:13and we are moving towards 2025 and if I
- 00:00:16talk about or give you a brief summary
- 00:00:18about this specific year with respect to
- 00:00:20the development of generative AI right
- 00:00:22in the field of generative AI we saw
- 00:00:24various llm models we saw Tech Giants
- 00:00:26competing between themselves to probably
- 00:00:29create the LM models in terms of uh you
- 00:00:32know applications in terms of content
- 00:00:34generation and many more uh we as a
- 00:00:37developer obviously we like we love to
- 00:00:39learn all those things so we also
- 00:00:41thought of using different different
- 00:00:43Frameworks and how we could probably
- 00:00:45integrate this kind of llm models and
- 00:00:47create some amazing custom chat Bots I
- 00:00:49think in this entire year we have
- 00:00:51specifically done this if I talk
- 00:00:53probably talk from the mid of this
- 00:00:54particular year there is something
- 00:00:56called as AI agents or agentic AI that
- 00:00:58have actually come you know uh companies
- 00:01:01have started talking more about multi-
- 00:01:03aai agents you know or we also say
- 00:01:05agentic AI you know so in this specific
- 00:01:08video uh I will be talking about what
- 00:01:11exactly agentic AI is because the reason
- 00:01:13of making this specific video is that
- 00:01:15what I feel uh now in this particular
- 00:01:17field of generative AI if I probably see
- 00:01:19in the upcoming years uh there are many
- 00:01:22many people who are going to work on
- 00:01:24this specific skill set that is agentic
- 00:01:26AI now what exactly is agentic AI how is
- 00:01:29is it different from generative AI I
- 00:01:31will be covering each and everything in
- 00:01:33this specific video along with this uh I
- 00:01:36will also be talking about which all
- 00:01:38Frameworks you can specifically use uh
- 00:01:41to probably create this agentic AI
- 00:01:43applications you know and uh if you
- 00:01:46probably see that while we go in 2025 I
- 00:01:49am going to probably cover many many
- 00:01:51many Frameworks and build amazing end to
- 00:01:53endend use cases with the help of
- 00:01:55agentic AI application and I'm also very
- 00:01:57near to launch my own mock interview
- 00:02:00platform initially we created that as a
- 00:02:02generative AI application now we also
- 00:02:04converting that into an agentic
- 00:02:05application now to understand all these
- 00:02:08things uh first of all let me just go
- 00:02:10ahead and share my screen and here uh in
- 00:02:13this particular video I will be making
- 00:02:15you understand about what exactly
- 00:02:16agentic AI is okay so uh till now
- 00:02:20whenever we used to probably talk about
- 00:02:22generative AI you know uh we used to
- 00:02:24probably say that hey we have some kind
- 00:02:26of models which will be able to help us
- 00:02:29create content
- 00:02:31right now here we are specifically using
- 00:02:35any kind of llm models right so let's
- 00:02:37say open a llm models or open source llm
- 00:02:40models Lama 3 different different llm
- 00:02:43models so if I probably consider these
- 00:02:44llm models our main task was that we
- 00:02:48used to query let's say a user is
- 00:02:53querying user used to put some kind of
- 00:02:56query and then what we used to do is
- 00:02:58that uh along with this llm model we
- 00:03:00also need to write a specific prompt
- 00:03:03like how this llm model needs to behave
- 00:03:06let's say I may probably say that hey
- 00:03:07you need to probably act like a author
- 00:03:10and you need to probably create a poem
- 00:03:12on this specific query whatever query we
- 00:03:15are trying to ask over here or the user
- 00:03:17is trying to ask and then based on this
- 00:03:19we used to specifically get some kind of
- 00:03:22output right so if we see in this
- 00:03:25particular flow the reason we used to
- 00:03:28say this as a generative AI because at
- 00:03:29at the end of the day it is creating or
- 00:03:32it is generating it is generating
- 00:03:35content right it is generating content
- 00:03:38and this is what is all about generative
- 00:03:40AI application you can probably finetune
- 00:03:42the prompt you can make this llm model
- 00:03:45behave in a better way you can probably
- 00:03:46create custom chat Bots uh we can modify
- 00:03:49this prompt we can uh we also say it as
- 00:03:52prompt finetuning you can probably make
- 00:03:55sure to write a right kind of prompt so
- 00:03:57that you will be able to get the right
- 00:03:58output but if I talk with respect to
- 00:04:02agentic AI application okay so agentic
- 00:04:04AI
- 00:04:05application now whenever we talk about
- 00:04:08agentic AI or let's talk about this
- 00:04:11agentic AI these are nothing but these
- 00:04:14are
- 00:04:15autonomous
- 00:04:17autonomous AI
- 00:04:19system okay autonomous AI system now
- 00:04:23let's say uh when we were specifically
- 00:04:26talking with respect to generative AI
- 00:04:28application there were also some
- 00:04:29applications that we used right like
- 00:04:31let's say rag right rag rag application
- 00:04:35I hope everybody has heard about it now
- 00:04:37what rag application basically does is
- 00:04:39that you know these llm models uh are
- 00:04:42not currently trained with the recent
- 00:04:44data you know it is regularly trained
- 00:04:47every 6 months every 8 months every year
- 00:04:50right but when I probably say today what
- 00:04:52we have this recent data in the internet
- 00:04:54it has not been trained with that you
- 00:04:56know if I probably ask any llm model hey
- 00:04:58what is the current news that I have
- 00:05:00right can you probably talk about the
- 00:05:01top AI news five top AI news then this
- 00:05:05llm model will not be able to answer it
- 00:05:07so what happens is that whenever a user
- 00:05:09try to query you know this llm model
- 00:05:11needs to also have access to something
- 00:05:15like an external external tool okay or
- 00:05:18external Source I can probably say this
- 00:05:21as external
- 00:05:23Source right now right now this
- 00:05:26particular exis is not there so what we
- 00:05:28do is that if you probably use some
- 00:05:30Frameworks like Lang chain and all we
- 00:05:32have something called as tools right one
- 00:05:35of the tool can be Doug dug go search I
- 00:05:38hope everybody has heard about this this
- 00:05:40basically helps you to do the Google
- 00:05:43search or uh do the search uh with
- 00:05:46respect to the recent news that are
- 00:05:47there in the internet okay you also have
- 00:05:49some other tools like let's say I want
- 00:05:51to specifically use uh Wikipedia search
- 00:05:54right so I can have Wikipedia tool for
- 00:05:58this and langin probably every tool is
- 00:06:00basically created if you also want to
- 00:06:02probably explore some other tool like RF
- 00:06:05so that is also available so Lang chain
- 00:06:07what it did is that it came up with this
- 00:06:09kind of various tools which you can
- 00:06:11probably integrate along with the llm
- 00:06:13applications to generate some kind of
- 00:06:15content okay but see you may be thinking
- 00:06:19if this external tools are there why
- 00:06:21can't we probably create autonomous AI
- 00:06:23system that can be able to perform this
- 00:06:25their own task now see guys over here
- 00:06:28when I I talk about autonomous AI system
- 00:06:30you know with respect to agent AI there
- 00:06:33is a specific goal to achieve right and
- 00:06:36while achieving this particular goal
- 00:06:38this all AI system will be working
- 00:06:41independently without any human
- 00:06:43intervention okay to achieve this
- 00:06:45specific goal okay now in this
- 00:06:47particular case if let's say that I
- 00:06:50require one tool so I may integrate if I
- 00:06:52require another tool that may also get
- 00:06:54integrated if I may uh probably use one
- 00:06:56more tool it may also get integrated
- 00:06:58right so those kind of tools you can
- 00:07:00manually integrate it if you have also
- 00:07:03used Lang graph okay Lang graph is one
- 00:07:06amazing uh module that has been coming
- 00:07:09by Lang chain you know and here also you
- 00:07:10can probably create agentic AI
- 00:07:12applications right uh this is also one
- 00:07:15of the Frameworks that you can
- 00:07:16specifically use but I hope you're
- 00:07:18understanding what is the basic
- 00:07:19difference between generative Ai and
- 00:07:20agentic AI in generative AI the main aim
- 00:07:24is just to create the content right if
- 00:07:26you are trying to make this applic ation
- 00:07:30uh have access to an external Source
- 00:07:33right here the workflow becomes quite
- 00:07:36complex because I have to keep on adding
- 00:07:38one or the other tool one or the other
- 00:07:40tool and there is no such end goal over
- 00:07:42here the main aim of this llm models is
- 00:07:45just to create content now similarly
- 00:07:47what we have actually done this agentic
- 00:07:50AI that is basically coming recently
- 00:07:52right it is really becoming popular many
- 00:07:54cosos are actually talking about it uh
- 00:07:56even Microsoft coo has said that hey
- 00:07:58this is probably going to replace the
- 00:08:01SAS products you know and it is it may
- 00:08:04be true guys because the application is
- 00:08:06quite amazing so as I said when compared
- 00:08:09to generative AI where the main name is
- 00:08:11not to probably create content as the
- 00:08:14goal here the goal will be based on the
- 00:08:16business outcome that you really want to
- 00:08:18do right business outcome business
- 00:08:22outcome and the best thing will be that
- 00:08:24this autonomous AI agents can have a
- 00:08:28very complex
- 00:08:30workflow very complex workflow right and
- 00:08:36this complex workflow will get executed
- 00:08:39independently to achieve this goal right
- 00:08:43and parall as this task is being
- 00:08:46probably completed right if it is
- 00:08:48getting completed this autonomous AI
- 00:08:51system can also fine tune themselves to
- 00:08:54perform much more better to perform much
- 00:08:59more better and this was not there in
- 00:09:02generative AI applications right so that
- 00:09:04is the reason there are so many
- 00:09:05Frameworks that are coming there's some
- 00:09:07Frameworks like Lang Lang graph there is
- 00:09:09framework like langlow there is a
- 00:09:11framework like fi data I'll also show
- 00:09:13you one amazing end to end examples
- 00:09:15which I have probably implemented for
- 00:09:17you okay now this is with respect to the
- 00:09:19agentic AI right now let me talk about
- 00:09:22some of the examples so that you get a
- 00:09:23complete idea like how this autonomous
- 00:09:25AI system works let's say that my task
- 00:09:27is probably to create
- 00:09:29a custom bot okay custom bot and this
- 00:09:34bot has uh this bot is nothing but it is
- 00:09:37an agentic AI application okay agentic
- 00:09:41AI application which probably interacts
- 00:09:44with many many things okay let's say my
- 00:09:47main goal is that this custom bot main
- 00:09:51goal is that whenever I ask any
- 00:09:54query I ask any query let's say that I
- 00:09:56ask this bot related something related
- 00:09:59to finance I'll say that hey I have
- 00:10:02$1,000 okay I want to probably buy some
- 00:10:06stocks buy some stocks and let's say
- 00:10:10that this is this particular stocks I
- 00:10:12want to sell it in 5 days sell in 5 days
- 00:10:17and I want a minimal profit of 50% let's
- 00:10:19say I'm just putting some context this
- 00:10:22is my goal that I really want to do I
- 00:10:25have probably kept a goal right now as
- 00:10:28soon as I do this
- 00:10:30now what this custom bot is basically
- 00:10:32going to do which is like an agentic AI
- 00:10:35this is going to create a complex
- 00:10:37workflow now the workflow let's say we
- 00:10:40have created a workflow this should be
- 00:10:41dependent on your uh Finance news let's
- 00:10:45say for finance news we can use YT YT
- 00:10:48Finance right so YT Finance
- 00:10:51functionality is also there YT Finance
- 00:10:53actually helps you to get all the stock
- 00:10:55details how the performance is like all
- 00:10:58the information that is probably there
- 00:10:59in the website right and this custom bot
- 00:11:02is just like an llm model this llm model
- 00:11:05can take this particular information and
- 00:11:07start working on it now along with this
- 00:11:09I may also require some other
- 00:11:11information what is the recent current
- 00:11:14news recent current news right so recent
- 00:11:18current news also so this referral
- 00:11:20should also be going now my workflow
- 00:11:22will look something like this first it
- 00:11:24goes and picks up all the detail related
- 00:11:25to finance news let's say that uh I just
- 00:11:28written by buy some stocks sell it in 5
- 00:11:30days get a 50% or let's say my query is
- 00:11:33that hey just let me know how is this
- 00:11:36Tesla stock okay how is this Tesla stock
- 00:11:39let's say uh I have something like uh
- 00:11:41okay I want to probably check what is
- 00:11:43this Tesla stock let me just uh change
- 00:11:46my pen okay okay perfect so let's say
- 00:11:51that I have a stock I want to probably
- 00:11:53compare and say that hey compare between
- 00:11:55Tesla and Nvidia and suggest me which
- 00:11:58one should I bu right so this if this is
- 00:12:01my question to my custom bot or to this
- 00:12:04agent AI application so the workflow
- 00:12:06will get started so my workflow will
- 00:12:08probably be in such a way that first of
- 00:12:10all I will go ahead and refer YT Finance
- 00:12:12okay I'll get the information about both
- 00:12:14the stock I will probably Compare the
- 00:12:16numbers the llm model will already
- 00:12:17Compare the numbers and I'll provide the
- 00:12:19information over there then my next flow
- 00:12:21will be that hey just go and see the
- 00:12:22current news like which what is a
- 00:12:25positive news what is a positive
- 00:12:26sentiment news that are probably there
- 00:12:28so I may probably go and see the top
- 00:12:30recent news right after this I may
- 00:12:32probably say that hey what kind of
- 00:12:34recent development is specifically
- 00:12:35happening right so this will also refer
- 00:12:38to some other news API right which is
- 00:12:40just acting like a tool right so this
- 00:12:43when I'm saying this is a tool this is
- 00:12:45basically an agentic AI application it
- 00:12:47is an autonomous AI Auto autonomous AI
- 00:12:51so this is a separate AI agent this is a
- 00:12:53separate AI agent this is a separate AI
- 00:12:55agent now this all executing together
- 00:12:58each and every task is basically handled
- 00:13:01by a separate autonomous AI agent right
- 00:13:04and they are working together they are
- 00:13:06executing this in a workflow right and
- 00:13:09finally after interacting with this you
- 00:13:11may get an output right you may get an
- 00:13:14output or the kind of suggestion that
- 00:13:15you probably looking for because what
- 00:13:17kind of question have you asked hey
- 00:13:18should I probably I I'll just say that
- 00:13:21hey go ahead and compare Tesla versus
- 00:13:22Nvidia stock and tell me which one
- 00:13:24should I buy so after doing all this
- 00:13:26after executing this entire workflow we
- 00:13:29will be getting a very good summary
- 00:13:31saying that hey what you really need to
- 00:13:32buy right this was not possible with the
- 00:13:35help of generative AI application
- 00:13:36because here the main aim is just to
- 00:13:39create content but if I talk about
- 00:13:41agentic AI application this has become
- 00:13:43much more smarter it is working
- 00:13:45autonomously and you can create any kind
- 00:13:48of complex workflow let's say you want
- 00:13:50to integrate multiple tools you want to
- 00:13:52integrate multiple AI autonomous agents
- 00:13:54you are able to do it and that is what
- 00:13:56is all about AI agents or agentic a
- 00:13:59right now what I am actually going to
- 00:14:02show you is that what all Frameworks you
- 00:14:04can specifically use and what I feel
- 00:14:07that in the upcoming years this
- 00:14:09Frameworks will be quite amazing because
- 00:14:11uh if I talk about I built my first
- 00:14:14agentic AI application 6 months back and
- 00:14:16now more and more amazing Frameworks are
- 00:14:18specifically coming up now these all
- 00:14:20Frameworks are open source and I'll also
- 00:14:22show you one end to endend example as we
- 00:14:24go ahead so let's go ahead and let's
- 00:14:26discuss about different different
- 00:14:27Frameworks but I hope you got an amazing
- 00:14:30example to to find out the differences
- 00:14:32between generative Ai and agentic AI
- 00:14:34right so guys now let us go ahead and
- 00:14:36probably discuss about some of the
- 00:14:38amazing Frameworks that are right now in
- 00:14:40there in the market which will actually
- 00:14:42help you to build about agent TK
- 00:14:43application once we specifically discuss
- 00:14:46about this I'm also going to show you
- 00:14:47one amazing end to end uh example where
- 00:14:49I've actually created a financial
- 00:14:51analyst which will actually help you to
- 00:14:53decide which stocks you can currently
- 00:14:55buy based on the recent information that
- 00:14:58we have have related to that particular
- 00:15:00stock price okay so here is one of the
- 00:15:03amazing framework which is called as F
- 00:15:04data now in that in this F data you will
- 00:15:07be able to create different different
- 00:15:08agents like legal agent financial
- 00:15:10analysis construction analyst marketing
- 00:15:13agent and these are like uh agentic AI
- 00:15:15application you can execute them in a
- 00:15:17specific workflow uh right now this is
- 00:15:20really really open source and uh here
- 00:15:23many many people are many many companies
- 00:15:25are specifically using it our end to end
- 00:15:27examples what we are basically going to
- 00:15:29do is that we going to use this and
- 00:15:31probably create that okay now uh you the
- 00:15:33best thing about this is that you will
- 00:15:35be able to integrate with any llm models
- 00:15:37that you specifically want from grock to
- 00:15:40Google Gemini to anthropic to cloudy to
- 00:15:43AWS to openi to Mistral anything that
- 00:15:46you specifically want okay then along
- 00:15:49with this you can also add any number of
- 00:15:51tools that you want right so it enable
- 00:15:53agents to integrates and interact with
- 00:15:55external system right so the autonomous
- 00:15:58AI system as said right hey let's
- 00:16:00probably if I ask hey which stock should
- 00:16:01I buy between Tesla or this I will
- 00:16:04probably go ahead and create an AI agent
- 00:16:06that AI agent will start uh you know
- 00:16:08communicating with the external uh apis
- 00:16:11News Channel or anything that you want
- 00:16:13right even you have options to integrate
- 00:16:15with payment Gateway and all right so
- 00:16:17that is the most amazing thing and is
- 00:16:19pretty much simple once I probably show
- 00:16:21you you can definitely have a look okay
- 00:16:23the next common and the famous uh um you
- 00:16:26know product or agentic AI framework
- 00:16:28work is nothing but Microsoft autogen
- 00:16:31right so this autogen is also coming
- 00:16:34like recently it is in the Talk of the
- 00:16:36Town and it it is again open source and
- 00:16:38it basically helps you to create a
- 00:16:40framework for agentic AI application
- 00:16:43along with this some more Frameworks
- 00:16:45that you can probably explore is
- 00:16:46something called as langlow now Lang
- 00:16:48flow I've already uploaded some videos
- 00:16:49in my channel this is a complete no code
- 00:16:53tool probably to develop your agentic AI
- 00:16:55applications which uh where you can also
- 00:16:58design complex workflows so uh yes you
- 00:17:01can probably do this and this is more
- 00:17:03like a drag and drop automatically your
- 00:17:05code your endpoint code will also be
- 00:17:07provided and you should also be able to
- 00:17:09deploy this in an amazing way so this is
- 00:17:11just one example here you can see uh
- 00:17:13user is probably creating an agent this
- 00:17:16agent is probably doing some kind of
- 00:17:18research uh the research is basically
- 00:17:20done based on the content research uh
- 00:17:22here you have different different API
- 00:17:24integration you can also go ahead and
- 00:17:25use your own prompting and many more so
- 00:17:28just to show you example let's say that
- 00:17:29I've created this simple agent over here
- 00:17:32and this is my entire uh you know
- 00:17:34workflow here you can see that I've I've
- 00:17:36used multiple agents URL calculator chat
- 00:17:39input dugdug go search and here I've
- 00:17:42used an agent with open Ai and finally
- 00:17:44I'm able to get the output once you
- 00:17:46probably create this you can also get
- 00:17:48your endtoend code over here so you just
- 00:17:51need to probably get your python API
- 00:17:52JavaScript API or python code whatever
- 00:17:55you like and you can integrate it and
- 00:17:56you can probably uh take it to that that
- 00:17:59entire Next Level okay then uh you have
- 00:18:02also one more amazing uh framework that
- 00:18:05is called as Lang graph and with respect
- 00:18:07to Lang graph here also you can create
- 00:18:09complex workflows uh if I consider Lang
- 00:18:11graph more complex workflows you can
- 00:18:13specifically create if I talk about data
- 00:18:15stack slang flow here you able to create
- 00:18:17complex workflow you can you can also
- 00:18:19use multiple agents as of your
- 00:18:21requirement multiple models multiple
- 00:18:23data preprocessing techniques multiple
- 00:18:25prompt techniques and all um here you
- 00:18:28can use Amazon Bedrock anthropic open AI
- 00:18:30cair Google generative AI Gro anything
- 00:18:33that you specifically want uh right now
- 00:18:35this is probably my favorite because
- 00:18:37with the help of this I'm able to create
- 00:18:39an application much more easier but yes
- 00:18:41my next year plan is to probably cover
- 00:18:43all this kind of amazing tools and
- 00:18:45develop some amazing end to end agent
- 00:18:49applications now let's go ahead and
- 00:18:51probably see one example I'll be using F
- 00:18:53data and I'll show you that how you can
- 00:18:55probably go ahead and create your own
- 00:18:57agent application
- 00:18:59so guys so here is one amazing endtoend
- 00:19:02agentic AI application uh where I'm
- 00:19:05specifically using open AI API key F API
- 00:19:08key here my main name is that I've
- 00:19:10created an agent which is called as web
- 00:19:12search agent and this main work is
- 00:19:14basically to interact with external
- 00:19:17thirdparty sources with respect to the
- 00:19:19recent news that we have so here you can
- 00:19:21see dougd Source search it is basically
- 00:19:23using the model it is using is open AI
- 00:19:25chat this is my web search agent along
- 00:19:27with that I also have a financial agent
- 00:19:29which is interacting with the Y Finance
- 00:19:30tool to get the stock market prices
- 00:19:33details and all and uh we can combine
- 00:19:35both the specific agent to probably
- 00:19:38create my entire playground where I will
- 00:19:40be able to create it in as a custom
- 00:19:42chatbot okay so here uh one amazing
- 00:19:45thing is that first of all we are
- 00:19:46creating an agent and inside that agent
- 00:19:48we can have any number of tools and
- 00:19:50model integration similarly over here
- 00:19:52this is my financial agent but
- 00:19:54internally you'll be able to see that it
- 00:19:56is interacting with tools like why
- 00:19:58Finance tool and it is using a model
- 00:19:59like open AI chat right and similarly we
- 00:20:01can probably use different different
- 00:20:03combination now this kind of projects I
- 00:20:06will also be coming up uh probably
- 00:20:08implementing everything from scratch but
- 00:20:10here I actually used this F data now
- 00:20:13this is running uh and here uh let's go
- 00:20:15ahead and probably check this in my um f
- 00:20:19data once you need to probably log in
- 00:20:20you'll be able to check it out in in the
- 00:20:22form of demo over
- 00:20:24here so guys now I am inside this
- 00:20:27particular playground of data. app all
- 00:20:29you have to do is probably login and
- 00:20:31right now you can also see that my code
- 00:20:33is running over here all I have to do is
- 00:20:35that I have to probably connect to an
- 00:20:36endpoint so the current my endpoint is
- 00:20:38basically running in Local Host uh 777
- 00:20:42okay and uh here you'll I'll just see
- 00:20:45that I'll just go ahead and ask hey what
- 00:20:46is your special skill okay and uh here
- 00:20:49you can probably see my answer right
- 00:20:52whether you need financial analysis St a
- 00:20:54recommendation or anything you'll be
- 00:20:55there to help right so now let's go
- 00:20:57ahead and ask some more questions uh
- 00:20:59I'll say hey can you
- 00:21:01provide
- 00:21:03me uh can you suggest me which stock to
- 00:21:10buy um is it
- 00:21:15between Tesla and Nvidia okay so let's
- 00:21:20say that this is my question okay and
- 00:21:23now here you can see that entire things
- 00:21:25are basically running yeah so I'm able
- 00:21:27to get the answer see over here Nvidia
- 00:21:29so and so this is the price overall hold
- 00:21:32based on the data analyze strong
- 00:21:34Contender Manus uh Nvidia shows strong
- 00:21:38buy Tesla also shows strong buy but the
- 00:21:41number is 12 or six buy 48 hold 4 so it
- 00:21:45appears to be a stronger Contender with
- 00:21:47an un strong buy recommendation this so
- 00:21:50here what is basically happening is that
- 00:21:51internally agents is basically getting
- 00:21:53called all the information from the
- 00:21:55stocks is basically getting up over here
- 00:21:57let's say that if I want to probably go
- 00:21:59ahead and click on this I will also be
- 00:22:00able to get maximum information as we
- 00:22:02can so it is probably taking all this
- 00:22:04information and based on that it is
- 00:22:06making this kind of decision so why we
- 00:22:09say this as agentic AI because
- 00:22:10internally all these agents has been
- 00:22:12calling this is basically interacting
- 00:22:14with this kind of uh uh external tools
- 00:22:18it is working in the form of a workflow
- 00:22:20right so I hope you like this particular
- 00:22:22video as we go ahead I've also created
- 00:22:24this kind of projects it'll be coming in
- 00:22:26my YouTube channel how you can probably
- 00:22:27go ahead and start from Basics so yeah
- 00:22:29this was it from my side I hope you like
- 00:22:31this particular video I'll see you in
- 00:22:32the next video itself thank you have a
- 00:22:34great day
- Agentic AI
- Generative AI
- AI Frameworks
- LLM Models
- Autonomous Systems
- Finance
- Chatbots
- Workflow Automation
- Data Analysis
- Artificial Intelligence