What Is Agentic AI and How Does It Work? | Agentic AI Tutorial | Agentic AI Explained | Simplilearn

imagine you are managing a global supply chain company and where you have to handle orders shipments and demand for casting but unexpected issues arises where sudden shortages like transport delays and the changes in demand so instead of relying on manual adjustments what if an AI agent could handle everything automatically this AI wouldn't just suggest actions it would decide execute and continuously improve its strategies That's The Power of agent Ki with that said guys I welcome you all on our today's tutorial on what is Agent Ki now before we move on just a quick info guys

simply learn has got Advanced executive program in applied generative AI with two-day immersion at IIT Madras campus you'll be getting certificate from iitm prak master classes by itm and top I's faculty and Alum so guys hurry up now and join the course the course link is mentioned in the description box now let us start with understanding first the first wave of artificial intelligence which was Predictive Analytics or we could say data analytics and forecasting what exactly happened uh like predictive AI focused more on analyzing the historical data identifying the patterns and making forecast about the

future events and these model do not generate any new content but instead it was predicting outcomes based on the statistical models and machine learning now technically how used to work so basically what we had like we used to take uh suppose this is the ml model okay so this is taking a structured data which could be like suppose any past user activity or it could be a transaction record or any sensor reading for example you can consider say Netflix users watch History okay it could be any movie genre watch time and the user rating so

now after this what we were basically doing this we were doing the feature engineering or pre-processing okay now in the fure uh Engineering Process we were extracting key features like user watch time Trends preferred genn rates and watch frequency and we could also apply scaling normalization and encoding techniques to basically make data more usable for the ml model then we were using the ml models suppose it could be a Time series forecasting models like ARA lstm and all those given algorithms which was basically predicting the Future movie preferences based on the historical data and in

the output guys Netflix AI recommends new shows or movie based on the similar user patterns so this is how exactly the Netflix model was working incorporating the machine learning model so this was exactly the first wave of AI now let us discuss about the second wave of AI now if I discuss about the second wave which was basically content creation and use of conversational AI so you know LM models like chat GPT became very much popular during the second wave of artificial intelligence so what exactly was happening like generative AI was taking input data and

it was producing new content such as text images videos or even code and these models learn from patterns in large data sets and it was generating humanlike outputs now let us bit understand how exactly this technology was working so basically first there was a data input okay so basically any prompt from the user so suppose in the GPT okay so I'll just open GPT all over here and say we are uh suppose we are giving any new prompt say such as write article on AI Okay so this was our given prompt and after this what

exactly was happening was tokenization and pre-processing so the input text suppose which I have written all over here write a article on AI so this text was basically split into smaller parts for example like uh you could consider certain thing like this so here you have right as one uh you know and as next and similarly you could carry on you know for the other words then what exactly used to happen that these words were you know uh converted into word embance means the numerical vectors represent words like in a higher dimensional space and then

we used to perform neural network processing so here uh the llm processes input such as attention mechanisms okay or you know using uh these models like gp4 bird and llama and with the help of self attention layers they were understanding the context and they were predicting the next word okay now as a result you were getting output certain thing like this so which was basically a generative AI phase so this was guys our second evolution of AI now if I talk about our third wave so it is basically agentic AI or autonomous AI agent now

what is this guys so the agentic AI actually goes beyond text generation so it integrates decision making action execution and autonomous learning these AI systems don't just respond to prompts but they also independently plan execute and optimize the processes so you could understand something like this so so here the first uh step was the user input or receiving any goal so user provides any high level instruction for example it could be like say optimize Warehouse shipments for maximum efficiency it could something be like that and unlike generative AI which would generate text agentic AI executes

real world actions after this what suppose The Prompt that we have given like optimize Warehouse shipments for maximum efficiency then the next step would have been quering the databases the AI would pull the real-time data from multiple sources so it could be traditional database like SQL or no SQL where we are fetching inventory levels or shipment history then it could be a vector uh database from where it is receiving some unstructured data like past customer complaints and all those things then with the help of external apis it is connecting to like forecasting Services all fuel

price apis or supplier Erp systems and these things are like present with this uh respect then uh the third step was the llm decision making now after quaring the database the AI agent processes data through the llm based reasoning engine example like decision rules applied like suppose if inventory is low then it could automate supplier restocking orders like if shipment cost is increasing then it is rerouting shipments through cheaper vendors and suppose also if weather condition impact the route then it is adjusting the delivery schedules now you can understand how agentic AI is behaving all

over here in the decision making process now next step would be action execution via apis so AI is executing task without human intervention it is triggering an API call to reorder a stock from A supplier or update the warehouse robot workflows to prioritize fast moving products or even send emails and notifications to logistic partners and about the changes what is going to be happen and after this finally it is continuously learning which is a data flywheel all over here okay the AI is monitoring the effectiveness of its action like U it was restocking effic or

did routing shipments you know reduce the cost and all so it is mon monitoring the effectiveness of the action it has taken and the data flywheel is continuously improving the future decisions so basically it is using reinforcement learning and fine-tuning to optimize its logic okay now let's have a just quick recap about the comparison of all these three waves of AI so basically creative ai's main focus was on forecasting the trends okay while generative AIS was creating the content and agentic AI on the other hand which is at the final step right now is making

decision and taking action so you could see how the evolution happened of AI in all these stages and if you uh understand about the learning approach then predective AI was basically analyzing the historical data while generative AI was learning from the patterns like using text image generation okay and but agent is basically using the reinforcement learning or the self learning to improve its learning approach now if we just look at the user involvement in productive AI so human is asking for the forecast and all here human is giving the prompts but in the agent AI

the prompts are the intervention of human input has become very much minimal if you could understand the technology like basically predictive VI was using machine Learning Time series analytics so these kind of you know uh algorithms they were using generative AI was using Transformers like GPT llama BT and all those things now agentic ai is doing what guys it is using llm plus apis plus autonomous execution so we have discussed how this workflow is you know in a short way how it is working and uh moving ahead we are also going to discuss uh through

an example how exactly all these steps like agent AI is working so based on the example you could understand like uh predictive AI you know Netflix recommendation model which they have on their system and uh similarly if we talk about U generative AI then you could understand about chat GPT you know writing articles and all those things and agentic AI we could imagine like how AI if Incorporated in Supply chains how you know things are working out so guys I hope so you would have got a brief idea regarding the three waves of AI now

let us move ahead and bit understand about what is exact difference between generative Ai and agentic AI now guys let us understand the difference between generative Ai and agentic AI so let us first you know deep dive into what exactly is a generative AI okay so as you can see all over here that generative AI models generally are taking input query okay and they are processing it using llm or large language model and basically returning a static response without taking any further action so in this case for example a chatbot like uh Chad GPT you

know it is taking the inut from the user so as I've shown you earlier that say suppose I've given an input like write a blog post on AI in healthcare so when I have written this uh given uh you know user input or given the query so when it goes to the large language model this model is actually you know tokenizing all these input query and it is retrieving the relevant Knowledge from its training data and it generate text based on the patterns now we give the prompt then llm processes it okay and then we

are getting the given output so now this is basically how you know generative AI is working so you could see all over here we have GPT model we have Del we have codex so these are some of the you know amazing you know generative AI uh models okay now let us discuss bit about Del which is actually a you know realistic image generation you know gen so uh like Del is described as you know the realistic image generation model model by the open Ai and this actually is a part of you know generative AI category

alongside with GPT which is basically for human like language creation purposes this model was created and you could have also codex for like uh it could be used for advanced code generation purposes so let us discuss a bit about Dal so di is like a deep learning model basically which is designed to generate realistic images from the text prompt and it can create highly detailed and creative visuals based on descriptions provided by the users so uh some of the aspects of di like you could have all over here like text to image generation where users

can input text prompts and Del can generate Unique Images based on those description the images generated by di are highly realistic and creative okay and it can generate photo realistic images artistic illustration and even surreal or imaginative visuals we would also have customization and variability where it is allowing variation of an image edits based on text instruction and multiple style so this is also part of a generative AI model and uh it is this tool is actually playing a very amazing role so I will show you one example like how generative AI is actually working

in the Mage generation purposes so guys as you can see all over here I have opened this generative VI tool called di let us give a prompt to Del and let's see how the image is generated so let's say we want have a futuristic city at Sunset filled with neon skyscrapper they have flying cars and holographic Billboards streets are bustling with humanoid robots and we can have people wearing uh let's just say Hightech you know let's include some technology okay now let us see how uh di is trying to create a image so this is

how actually generative AI is working so let us wait for a few seconds as the output comes up now you could see all over here that uh this image which is generated basically this is generated by Ai and you could see based on our prompt it has given like the kind of you know uh the input we gave and we got the output based on this now so this is one of the amazing uh gen tool we could explore this guys okay now guys let us discuss about agentic AI or autonomous decision making and action

execution so you can see this diagram all over here so agent itic AI like unlike the generative AI it is not generating responses but it is also executing a task autonomously based on the given query for example like if you take uh AI in managing a warehouse inventory okay suppose we want to optimize the warehouse shipment for the next quarter so here what is going to happen so first the agent is going to receive its goal all over here okay and U this AI agent uh you know is going to query the external data sources

so it could uh you know for example it could be your uh you know inventory databases or Logistics API and then it retrieves real time inventory levels and it demands the given forecast okay now at here it is going to make the autonomous discussions and the kind of output we are going to get will be kept in observation by this agent okay so basically it is going to analyze the current Warehouse stock product demand for the next quarter check the suppliers avail ility and automate the restocking if inventory is below the given threshold so U

for example you could uh imagine uh you know suppose based on the you know output what we are going to get all over here so based on this output we could uh get certain thing like this like uh say current inventory level like say 75% capacity okay then uh it could have also other thing like uh say demand forecast say 30% increas in expected in quarter 2 and also it is going to go say like say reordering initiated so this is output what we are going to get based on the Supply Chain management and example

what we are trying to get so as we have seen in generative AI user is giving the input okay prompt then it is using llm model to generate the given output but agentic AI is doing what guys it is going it is going to take action you know beyond just generating a text so in this scenario it is ing the inventory databases it is automating the purchase order it is going to select the optimal shipping providers which could be you know suitable for the given company it is going to continuously refine the strategies based on

the realtime feedback so guys let's recap Once More so if we talk about the function base then J is more concerned with producing a written content or a visual content okay and even it can code from the pre-existing input but if you talk about agent AI guys uh it it is actually you know it's all about decision making taking actions towards a specific goal and it is focused on achieving the objectives by interacting with the environment and making the autonomous decision gen is exactly relying on the existing data to predict and generate content based on

say patterns it has learned during its training phase but it does not adapt or evolve from its experiences whereas if I talk about agentic AI it is adaptive so it is learning from its actions and experiences it is improving over time by analyzing the feedback adjusting his behavior to meet objectives more effectively with the help of genni human input is essential to The Prompt so that you know basically with the help of that it could go into the LM model and it could generate the given uh you know output based on your prompt once uh

you set up the agentic AI it requires like minimum human involvement it operates autonomously making decisions and adapting to changes like without continuous human guidance and it can even learn in real time so that's the beauty of agentic so we have given one example of gen like basically giving prompt to the chat GPT or di okay and agentic AI one example could be your Supply Chain management system now let us bit deep dive into understanding the technical aspects of how agent AI is exactly working now guys let us try to understand how agentic AI is

exactly working so there is actually a four-step process of you know how agentic AI exactly works so the first step is you know perceiving where basically what we are doing is we are gathering and processing information from databases sensors and digital environments and also the next step is reasoning so with the help of large language model as a decision-making engine it is generating the solutions if we talk about the third step which is is acting so it is integrating with external tools and softwares to autonomously execute the given task and finally it is learning continuously

to improve through the feedback loop which is also known as the data flyy okay now let us explore each of the step one by one and let us try to understand so if you talk about perceiving okay so this is actually the first step where agentic AI is actually stepping up so it is doing the perception where what exactly is happening guys that AI is collecting data from multiple sources so this data could be from database okay like your traditional and Vector databases okay so it could be graph Q like vector database means the same

and if you talk about other from data it could be from apis like it is fetching realtime information from external systems it is uh basically taking data from the iot sensors like for real world applications like Robotics and Logistics and also it could take you know data from the user inputs also like it could be text command voice commands or a chatbot interaction now how it is exactly working guys so basically let us recollect everything technically and let us see how this is happening so the first step which is going in perceiving is the data

extraction where uh exactly the AI agent queries the structured uh databases like SQL or no SQL for Relevant records uh it is also using Vector data bases to retrieve any semantic data for context aware responses like it could be you know any complaint certain uh you know it is trying to find out okay so next after it has got the data extraction it goes for feature extraction and pre-processing where AI is filtering the relevant features from the raw data for example like a fraud detection AI is scanning the transaction log for anomalies the third thing

it is entity recognition and object detection so AI uses basically computer version to detect objects and images and uh then it applying the named entity recognition this is a technique okay uh to extract the critical terms from the given text also so we have three uh step by-step process which is happening in uh perceiving the first one is data extraction second one is feature extraction and pre-processing the third one is like entity recognition and object deduction so uh let us take a very simple example example like AI based customer support system so if it consider

an agentic AI assistance like for a customer service so say a customer is asking where is my order so the AI queries multiple databases all over here suppose it is going to query the e-commerce order database to retrieve the order status or it could go to the logistics API to track the realtime shipment location also it could go for customer interaction history to provide personalized response the result what we get all over here is that the AI is fetching the tracking details identifying any delays if it is happening and suggesting the best course of action

now uh the next step is reasoning okay now ai's understanding and decision making and problem solving is making agentic AI very uh greater so here what is exactly happening like once the AI has perceived the data now it should start reasoning it okay so the LM model acts as a reasoning engine you know orchestrating a processes and integrating with specialized models for various function so if you talk about the key components uh like here used in the reasoning it could be llm based decision making so AI agents could use models like llms like gbt 4

Cloud llama to interpret a user intent and generate a response it is basically coordinating with smaller AI models for domain specific task like it could be like Financial prediction or medical Diagnostics so these could be uh you know given example then it is using a retrieval augmented generation or RG model okay to with the help of which AI is enhancing the accuracy you know by retrieving any propriety data from the company's databases for example like instead of relying on GPT 4's knowledge the AI can fetch company specific policies to generate the accurate answers so this

could be the one and uh in in the reasoning the final step is AI workflow and planning so it is a multi-step reasoning where AI is breaking down complex task into logical step for example like if asks to automate a financial report AI is retrieving the transaction data analyzing the trend and it is formatting the results Al so for example you could use this in uh Supply Chain management suppose consider there is a logistics company which is using the agentic AI to optimize what could be the you know uh shipping routs you know so a

supply chain manager requesting the AI agent to find the best shipping route to reduce the delivery cost so the AI processes realtime fuel prices traffic conditions and weather report so using llm Plus data retrieval it finds out the optimized routs and selects the cheapest carrier result you get is that AI chooses the best delivery option so here the cost is reduced and improving efficiency but this is one of the uh use cases guys uh so after perceiving you get his reasoning okay now let us move ahead and discuss about the third step which is act

so in this step basically what is happening like AI is taking autonomous actions so unlike generative AI which stops at generating content so agentic AI takes uh the real world action okay how AI is executing task autonomously guys so basically first step is like here the integration with apis and software could be happened where AI can send automated API calls to the business systems for example like reordering the stock from the supplier Epi so suppose any inventory level is going down so it could you know reorder that particular stock from the suppliers API so it

is interacting with the given API now it could also automate the workflows like AI executes multi-step workflows without human supervision so here like AI can handle like insurance claims by verifying the documents checking policies and approving the payouts and finally AI could operate within predefined business business rules okay to prevent any unauthorized actions also so ethical AI is basically being worked in this direction for example like AI can automatically process claims up to say uh $10,000 you know but it is requiring the human approval for the higher amounts So based on you know insurance and

policy making stuff so agentic AI could be you know really helpful in this scenario uh one example like uh let's consider so let's say we have this agentic AI managing an IT support system so suppose a user says my email server is down so the AI can diagnose the issue restart the server and confirms the given resolution now if it is unresolved then AI escalates to a human technician then uh it results into you know AI is fixing the issues autonomously reducing the downtime okay so this is where your action or act is coming up

into the picture now if you go on to the next and the final step which is learning so uh learning basically with the help of data fly wheel it is continuously learning okay so this is the feedback loop all over here which is the data fly wheel so how AI learns over the time if we ask this question so what is exactly happening that it is uh interacting with the data collection suppose AI logs uh successful and failed actions for example like if users correct AI generated responses then AI is learning from those Corrections second

thing what you could do is you could model you could fine-tune the model and do reinforcement learning so AI adjusts its decision- making models you know basically to improve future accuracy it uses reinforcement learning basically to optimize workflows based on past performance okay now uh third step could be automated data labeling and self correction so here what is happening that AI is labeling and categorizing past interactions to refine its knowledge based example like AI autonomously is updating frequently Asked answers based on the recurring user queries so in this way AI is learning over the time

uh example one you could consider uh so say we have this uh AI is optimizing any financial fraud deduction so say this is uh consider that this is a bank which is AI powered which has this AI powered fraud detection system so AI is analyzing these financial transaction and it is detecting any susp ious activity and if Flagg the transactions are false and yeah is learning to reduce these false alerts so over the time AI is improving the fraud detection accuracy like minimizing disruptions for the customer so in this way AI is getting smarter over

the time like reducing the false alerts and also the financial fraud so let's have a just quick recap of what uh we studied right now so agentic AI Works in four steps the first step is perceiving where AI is gathering dat from databases sensors and apis the next step is reasoning so it is using llm to interpret task applies logic and generating the solution the third step is acting so here AI is integrating with external systems and automating the task and finally it is learning so AI is improving over the time you know via feedback

loop or which is basically called as data fly wheel so guys uh now let us say this diagram and try to understand what this diagram is trying to say so the first thing you could see an AI agent all over here so this is an AI agent which is basically an autonomous system so which has the capability of pursuing its environment making decision and executing actions without any human intervention now ai agent is acting as the Central Intelligence okay in this given diagram and it interacts with the user okay uh and various other data sources

it processes input queries databases makes decision using a large language model and it is executing action and it is learning from the given feedback now the next step you could see the llm model so if you talk about llms these are the large language model which is kind of an advanced AI model trained on massive amount of Text data to understand generate and reason over natural language now if I talk about this llm so This is actually acting as the reasoning engine all over here and it is interpreting the user inputs and making informed decision

it is also retrieving relevant data from the databases generating responses it can also coordinate with multiple AI models for different task like it could be content generation okay predictions or decision making now when the user is asking a chat board like for example let's say what is my account balance so the llm processes the query retrieves the relevant data and responds the given bank balance accordingly now if you look at the kind of database the llm is interacting so we have the tradition database and the vector database so uh here if I say uh the

database like AI agent basically squaring the structured database so suppose structured database like it could be a customer records or inventory data or it could be any transactional log also so traditional databases basically store well- defined you know structured information okay so for example like when a bank a assistant is processing a query like show my last five transaction so it is basically fetching the information from a traditional SQL based database next we have this Vector database also guys so Vector database is a specialized uh kind of a database for storing unstructured data which could

be like text embeddings images or audio representations so guys like unlike traditional databases that store exact values Vector databases store in a high dimensional mathematical space it allows AI models to search semantically uh similar data instead of like exact matches now ai is retrieving the contextual information from the vector databases which is ex actually enhancing the decision making it is improving the AI memory by allowing the system also to search for you know conceptually similar past interaction let us take a example to understand this for example uh we have discussed about a customer support chatbot

so suppose if it queries a vector database to find out similar pass tickets like when responding to a customer query so a recommendation engine could use a vector database to find out similar products on a users past preferences so this could be done in that scenario Alo some of the like popular Vector databases could be like Facebook's AI similarity search Pine Cone or vv8 these are the certain amazing Vector databases then you could see the next step is you know after it has worked on these given data it is performing the action so the action

component is refering where AI agent has this ability to now execute task autonomously after the reasoning is done so AI is integrating with external tools apis or automation software to complete the given task it does not provide only information but it is actually uh say you know performing the given action so for example like in a customer support the AI can automatically reset a user's password after verifying their identity if we talk about in finance then AI can approve a loan also like based on the predefined eligibility criteria now finally we have the data flywheel

so data flywheel is a continuous feedback loop where AI is learning from the past interactions refining its models and it is always improving over the time now every time like the AI is interacting with the data or taking an action or receiving a feedback that information is fed into this model so this is creating a self uh improving AI system that is becoming smarter over the time so the data fly is allowing AI to learn from every interaction and uh AI is becoming more efficient by continuously optimizing responses and refining strategies best thing in could

be used in a fraud detection so in this the AI is going to learn from the past fraud cases and it is going to detect new fraudulent patterns and more effectively chatbots also can learn from user feedback and improve the responses and finally you have the model customization which is basically you are trying to fine-tune the AI models on specific business need or any industry requirement so AI models are not static like they can be adapted and optimized for a specific task so custom fine tuning is actually improving the accuracy and domain specific application like

it could be Finance Healthcare or cyber security so a financial institution uh say fine-tuning an llm to generate an investment advice okay on the historical market trends that could be one use case or in healthcare if you disc us like the healthcare provider is fine-tuning then AI model to interpret the medical reports and recommend the treatments so guys based on the given diagram you would have got a brief idea like how uh you know agentic AI is working now if we discuss about the future of agentic a then guys I would say it looks very

much promising because it is keep improving itself and it is finding new ways to be useful like with better machine learning algorithms and smarter decision making these AI system will be more uh independent handling complex task on their own and believe me in Industries like healthcare Finance customer service they have already started to see how AI agents can make more impact and it could be more efficient from personalization perspective you know managing resources and many more other things so as the system continue to learn and adapt I think so they will be opening up even

more possibilities helping businesses grow improving how we live and work now I would say that uh in conclusion that agentic AI is actually Paving the wave for New Opportunities like unlike the older versions of AI which was assisting with generating content or predicting the data you know or responding to any queries but agentic AI can perform techniques independently with minimal human effort and agentic AI has become self-reliant in decision- making way and it is making very big differences in industry like Healthcare Logistics customer services which is enabling companies to be more efficient as a result

it is providing better services to their clients so guys that was all for today's video I hope so you would have enjoyed our today's video on agenti AI thank you guys for watching this video staying ahead in your career requires continuous learning and upskilling whether you're a student aiming to learn today's top skills or a working professional looking to to advance your career we've got you covered explore our impressive catalog of certification programs and Cutting Edge domains including data science cloud computing cyber security AI machine learning or digital marketing designed in collaboration with leading universities

and top corporations and delivered by industry experts choose any of our programs and set yourself on the path to Career Success click click the link in the description to know more hi there if you like this video subscribe to the simply learn YouTube channel and click here to watch similar videos turn nerd up and get certified click here