“NEURA -AI AGENT”
1
Table of Contents
Chapter 1: Introduction
1.1 Objective
1.2 Relevance of the Project
1.3 Problem Statement
Chapter 2: Literature Survey
2.1 Existing System
2.2 Proposed System
Chapter 3: System Requirement
3.1 Requirement Specification
3.1.1 Hardware Specification
3.1.2 Software Specification
3.2 Technology Used
Chapter 4: System Analysis & Design
4.1 Problem Statement
4.2 Feasibility Study
4.3 Design and Architecture
Chapter 5: Implementation
5.1 Purpose
5.2 Modules
2
Chapter 6: Screen Shots
Chapter 7: Conclusions
Chapter 8: References
3
Chapter 1: Introduction
1.1 Objective
The primary objective of the AI Agent project is to create an intelligent system that enhances
user interaction through natural language processing and machine learning. This AI Agent is
designed to assist users by automating routine tasks, which can include scheduling
appointments, retrieving information, and managing reminders.
The focus on natural interaction means that the AI Agent will be capable of understanding
and processing human language in a way that feels intuitive and seamless to users. By
leveraging advanced AI techniques, the system aims to provide personalized responses
tailored to individual user preferences and behaviors.
A key aspect of the project is its emphasis on continuous learning. The AI Agent will not only respond
to user queries but will also learn from interactions over time, adapting its responses and
functionalities based on user feedback and changing needs. This adaptability is crucial for improving
user experience, as it allows the AI Agent to become more effective and relevant in assisting users
with their specific tasks and challenges.
1.2 Relevance of the Project
In the current technology-driven landscape, AI Agents play a pivotal role in bridging the gap
between human users and complex digital systems. They simplify intricate workflows,
making it easier for users to navigate tasks that would otherwise require significant time and
effort. The relevance of this project lies in its potential to enhance productivity and
accessibility to intelligent services.
Existing virtual assistants, while useful, often fall short in providing deep personalization and
contextual understanding. They may handle basic commands effectively but struggle with
more complex requests that require an understanding of user intent and context. This project
addresses these shortcomings by developing an AI Agent that can adapt to individual user
needs, thereby offering smarter assistance across various domains, such as personal
productivity, customer service, and information management.
4
As organizations and individuals increasingly rely on technology to manage their daily
activities, the demand for more sophisticated and responsive AI solutions continues to grow.
This project is relevant not only for its technical contributions but also for its potential to
improve user satisfaction and engagement with AI technologies.
1.3 Problem Statement
often encounter significant challenges in managing their time and accessing relevant
information efficiently. Current virtual assistants typically lack the ability to fully understand
nuanced or contextual requests, which can lead to user frustration and inefficient task
execution. For example, when a user asks a virtual assistant to "remind me to call John
tomorrow after my meeting," the assistant may struggle to interpret the context of "after my
meeting," resulting in a missed opportunity to provide a relevant reminder.
This project aims to address these issues by developing an AI Agent that comprehends
complex inputs and retains user context. By doing so, the AI Agent will be able to provide
personalized responses that enhance overall productivity and user satisfaction. The goal is to
create a system that not only responds to direct commands but also understands the broader
context of user interactions, allowing for a more fluid and effective user experience.
In summary, the AI Agent project seeks to fill the gaps left by existing systems by offering a
more intelligent, adaptable, and user-friendly solution that meets the evolving needs of users
in a fast-paced digital environment.
5
Chapter 2: Literature Survey
2.1 Existing System
In the realm of artificial intelligence, several popular AI assistants have emerged, including
Siri, Alexa, and Google Assistant. These systems have become household names, primarily
due to their ability to perform a variety of tasks that enhance user convenience.
Predefined Response Patterns:
These AI assistants operate largely on predefined response patterns. This means that they are
programmed with specific responses to a set of common queries. For instance, if a user asks,
"What’s the weather today?" the assistant retrieves data from a weather service and delivers a
standard response. While this approach works well for straightforward questions, it limits the
assistant's ability to engage in more complex interactions.
Limited Learning Capabilities:
One of the significant drawbacks of existing AI assistants is their limited learning
capabilities. While they can learn from user interactions to some extent, this learning is often
superficial. For example, they may remember a user’s name or frequently asked questions,
but they struggle to adapt to changing user preferences or to understand the context of a
conversation over time. This limitation becomes particularly evident in multi-turn
conversations, where the context established in earlier exchanges is crucial for accurate
responses.
Contextual Understanding:
Current systems often fail to grasp the nuances of human language, especially in complex
scenarios. For instance, if a user says, "Remind me to call John after my meeting," the
assistant may not understand what "after my meeting" refers to, leading to ineffective
reminders. This lack of contextual understanding can frustrate users and diminish the overall
effectiveness of the assistant.
Need for Dynamic Adaptation:
Research in the field of AI indicates a growing need for systems that can dynamically adapt
to individual users through continual learning. Users increasingly expect their AI assistants to
6
provide personalized experiences that evolve based on their interactions. This demand
highlights the necessity for more sophisticated AI Agents that can learn and adapt in real-
time, improving their utility and user satisfaction.
2.2 Proposed System
In response to the limitations identified in existing systems, our proposed AI Agent leverages
advanced technologies to create a more intelligent and responsive assistant.
Advanced Natural Language Processing (NLP):
The proposed system utilizes state-of-the-art natural language processing models that enable
it to interpret user commands with greater accuracy. By employing techniques such as deep
learning and semantic analysis, the AI Agent can understand the intent behind user queries
more effectively than traditional systems. This allows for a more nuanced understanding of
language, including idiomatic expressions and context-specific phrases.
Machine Learning Algorithms:
Incorporating machine learning algorithms allows the AI Agent to adapt over time. As users
interact with the system, it learns from these interactions, refining its responses and
improving its ability to predict user needs. This continual learning process is essential for
creating a personalized experience, as the system can adjust to changes in user behavior and
preferences.
Storing Interaction History:
Unlike existing systems, the proposed AI Agent maintains a comprehensive interaction
history. This feature enables the assistant to remember past conversations, user preferences,
and frequently requested tasks. By leveraging this stored information, the AI Agent can
provide personalized assistance that feels more intuitive and relevant to the user.
7
Multitasking Capabilities:
The proposed system is designed to support multitasking, allowing users to engage in
multiple interactions simultaneously. For example, a user could ask the AI Agent to schedule
a meeting while also requesting information about a different topic. This capability enhances
the user experience by making the assistant more versatile and efficient.
Seamless Integration of New Knowledge:
The AI Agent is built to integrate new knowledge seamlessly. As it encounters new
information or user requests, it can update its knowledge base without requiring extensive
reprogramming. This flexibility ensures that the assistant remains current and capable of
addressing a wide range of queries and tasks.
Enhanced User-Agent Interactions:
Overall, the proposed system aims to enhance the depth and quality of user-agent
interactions. By combining advanced NLP, machine learning, and personalized assistance, the
AI Agent aspires tcreate a more engaging and effective user experience. This approach not
only addresses the shortcomings of existing systems but also sets a new standard for what
users can expect from AI technology.
8
Chapter 3: System Requirement
3.1 Requirement Specification
3.1.1 Hardware Specification
Processor:
The recommended processor for the AI Agent project is an Intel i5 or higher. This choice is
crucial for efficient model execution, as the processor is responsible for executing
instructions and performing calculations. An Intel i5 processor provides a good balance
between performance and cost, enabling the AI Agent to handle complex computations
required for tasks such as natural language processing and machine learning.
RAM:
A minimum of 8 GB of RAM is required to support data processing and multitasking. RAM
(Random Access Memory) is essential for temporarily storing data that the CPU needs to
access quickly. In the context of the AI Agent, sufficient RAM allows for smooth operation
when running multiple applications or processing large datasets. Insufficient RAM can lead
to slow performance, increased latency, and a poor user experience, especially when the AI
Agent is required to handle multiple user requests or complex tasks concurrently.
Storage:
At least 500 GB of storage, either in HDD (Hard Disk Drive) or SSD (Solid State Drive)
format, is necessary to accommodate datasets, models, and logs. Storage capacity is vital for
maintaining the operational data of the AI Agent, including user interaction histories, machine
learning models, and any additional resources required for processing. An SSD is preferred
over an HDD due to its faster read/write speeds, which can significantly enhance the
performance of the AI Agent, especially during data retrieval and model loading.
Network Connectivity:
Reliable internet access is essential for cloud-based function calls and data transfer. The AI
Agent may utilize cloud services for various functionalities, such as accessing external APIs,
storing data, or leveraging additional computational resources. A stable and fast internet
connection ensures that the AI Agent can communicate effectively with these services,
providing timely responses to user queries and maintaining a seamless user experience. Poor
network connectivity can lead to delays, timeouts, and a frustrating experience for users.
9
10
3.1.2 Software Specification
Operating System:
The AI Agent is designed to be compatible with major operating systems, including Windows
10, Linux, or macOS. This compatibility ensures that the system can be deployed on a wide
range of devices, catering to different user preferences and environments. Each operating
system has its strengths, and supporting multiple platforms increases the accessibility and
usability of the AI Agent. For instance, Linux is often preferred for server environments due
to its stability and performance, while Windows and macOS are popular for desktop
applications.
Programming Language:
Python is chosen as the primary programming language due to its rich ecosystem of AI
libraries and frameworks. Python is widely used in the field of artificial intelligence and
machine learning because of its simplicity, readability, and extensive community support. The
language's versatility allows developers to implement complex algorithms and models
efficiently. Additionally, Python's syntax is user-friendly, making it an excellent choice for
both beginners and experienced developers.
11
3.2 Technology Used
1. Programming Language
Python
Primary language for AI development, data processing, and automation.
Offers a rich ecosystem of libraries for speech, NLP, scraping, and ML.
2. Frontend Framework
Streamlit
Enables interactive UI for text and voice-based user interaction.
Simple, fast, and Python-compatible
3. AI Model Framework
Ollama
Lightweight LLM deployment engine supporting local model inference.
4. Models Used
Gemma3, Mistral
LLMs used for Q&A, summarization, and document understanding.
5. Speech Processing
SpeechRecognition: Converts voice to text.
pyttsx3: Converts text response to speech.
6. Document Handlin
PyPDF: Extracts and processes text from PDF files.
7. Data Retrieval & Vector Search
FAISS-CPU: Enables fast semantic search through vector embeddings.
8. LLM Integration
LangChain (Ollama & HuggingFace)
Manages interaction with language models and tool chaining.
9. Web Scraping
Requests: Fetches HTML content from web pages.
BeautifulSoup: Parses and extracts clean text from HTML.
12
Chapter 4 : System Analysis & Design
4.1 Problem Statement
In today’s rapidly evolving digital world, the demand for intelligent, responsive agents that
can assist users efficiently has grown tremendously. Despite advances in technology, many
existing AI assistants and virtual agents still face significant limitations. Below is a detailed
explanation of each critical problem that the AI Agent project aims to solve:
1. Lack of Deep Personalization
Many current AI assistants provide generic responses based on predefined templates or broad
user profiles. They often fail to deeply understand the unique preferences and habits of each
user. This lack of personalization limits their ability to offer tailored assistance, resulting in a
one-size-fits-all experience that may not address the specific needs and expectations of
individual users.
Example: An assistant might remind all users at generic times without adapting to a user’s
daily routine or preferred scheduling habits, causing inconveniences.
2. Poor Contextual Understanding
Context is crucial for engaging and helpful conversations. Present-day AI agents generally
process user requests as isolated messages without adequately incorporating prior dialogue or
the broader situational context. This results in misunderstandings or inappropriate responses,
especially during multi-turn conversations where commands depend on preceding
interactions.
Example: If a user says, “Schedule a meeting after my doctor’s appointment,” the AI may
misinterpret this if it doesn't recall the earlier mention of the doctor’s appointment time.
3. Limited Adaptability and Learning
Most deployed AI assistants exhibit limited ongoing learning capabilities. They might require
manual updates or retraining on new data and are slow to adapt to changes in user behavior,
13
preferences, or external circumstances. This hinders performance and reduces user trust over
time.
Example: An AI agent that can't remember user feedback or learning from mistakes may
continue making repetitive errors or provide out-of-date recommendations.
4. Inefficient Handling of Complex and Diverse Tasks
Current systems are often designed to manage simplistic, isolated tasks such as setting alarms
or answering factual queries. However, users often require AI agents to handle more
sophisticated workflows involving multiple interrelated tasks, decision-making, and
prioritization, which exceeds the capabilities of many existing assistants.
Example: Automatically coordinating meetings between several participants, rescheduling
conflicting appointments, and sending reminders requires complex understanding and task
orchestration.
5. Scalability and Extensibility Challenges
Many AI systems are built with rigid architectures that resist easy modification or extension.
As user needs expand or new functionalities are desired, these AI assistants struggle to scale
or adapt without substantial redevelopment efforts.
Example: Adding support for new languages, domains, or integration with third-party
applications can be complicated and resource-intensive.
6. Privacy and Data Security Concerns
Handling personal and sensitive data responsibly is paramount for AI Agents interacting with
users. Existing solutions sometimes inadequately safeguard user data, resulting in privacy
risks or data breaches, which erode user confidence.
Example: Users may hesitate to fully engage or share information with an AI agent fearing
misuse or unauthorized access of their data.
14
Summary
This project addresses each of these core problems by developing an AI Agent that:
Offers deep, personalized assistance by learning individual user preferences.
Maintains contextual awareness across conversations for coherent interactions.
Continuously learns and adapts from user interaction and feedback.
Manages complex, multi-step tasks efficiently.
Is built on a scalable, modular architecture for easy extension.
Ensures strict data privacy and security protecting user information.
15
4.2 Feasibility Study
The feasibility study is a critical assessment that determines whether the AI Agent project can
be successfully executed within the constraints of technology, resources, time, and budget.
This study evaluates three major aspects:
Technical Feasibility
Technical feasibility assesses whether the current technology and tools are sufficient for
implementing the AI Agent. This involves evaluating the maturity and capabilities of existing
AI frameworks and libraries. For instance, frameworks like TensorFlow and PyTorch provide
robust tools for building machine learning models, while libraries such as NLTK and spaCy
offer powerful natural language processing capabilities. Given the advancements in these
technologies, it is technically feasible to develop an AI Agent that can understand and
respond to user queries effectively. Additionally, the availability of cloud computing
resources allows for scalable processing power, further supporting the technical feasibility of
the project.
Operational Feasibility
Operational feasibility examines whether the AI Agent will be user-friendly and effectively
meet the needs of its intended users. This involves considering the user experience and the
system's ability to communicate naturally. The design of the user interface (UI) plays a
crucial role in this aspect, as it must be intuitive and accessible to users with varying levels of
technical expertise. The AI Agent's capability to automate routine tasks, such as scheduling
and information retrieval, is expected to enhance user productivity and satisfaction. By
focusing on user-centered design principles, the project aims to ensure that the AI Agent is
not only functional but also enjoyable to use.
Economic Feasibility
Economic feasibility evaluates whether the project’s implementation is cost-effective. This
includes analyzing the costs associated with hardware, software, and development. By
utilizing open-source software and cloud platforms, the project can significantly reduce
expenses, making it more economically viable. For example, using frameworks like
TensorFlow and libraries like NLTK eliminates licensing fees, while cloud services can
16
provide scalable resources without the need for significant upfront investment in hardware. A
thorough cost-benefit analysis will help determine if the expected benefits of the AI Agent
justify the investment required for its development and deployment.
Overall, this feasibility study ensures that the AI Agent project is not only theoretically sound
but also practical and sustainable in real-world conditions. It provides a foundation for
informed decision-making throughout the development process.
4.3 Design and Architecture
A well-defined design and architecture are essential for the successful implementation and
scalability of the AI Agent. The system is structured into modular components, each
responsible for specific functionalities, which promotes flexibility and maintainability.
User Interface (UI)
The User Interface (UI) serves as the primary platform for users to interact with the AI Agent.
It is designed to be intuitive, supporting both text and voice inputs to accommodate different
user preferences. A well-designed UI enhances user engagement and satisfaction, making it
easier for users to access the AI Agent's features. The UI may include visual elements such as
buttons, menus, and chat windows, as well as voice recognition capabilities to facilitate
natural interactions.
Natural Language Processing (NLP) Module
The Natural Language Processing (NLP) module is responsible for converting human
language inputs into machine-readable data. This module performs several key tasks,
including:
Tokenization: Breaking down text into individual words or phrases.
Syntax Analysis: Analyzing the grammatical structure of sentences.
Intent Recognition: Identifying the user's intent behind a query.
17
By accurately processing user inputs, the NLP module enables the AI Agent to understand
and respond appropriately to a wide range of queries.
Dialogue Manager
The Dialogue Manager maintains the context of the conversation, handling multi-turn
interactions and ensuring coherent communication. It tracks the flow of the conversation,
allowing the AI Agent to remember previous exchanges and respond in a contextually
relevant manner. This capability is crucial for providing a natural conversational experience,
as it enables the AI Agent to engage in more complex dialogues and follow up on user
requests effectively.
Knowledge Base
The Knowledge Base stores both static and dynamic information, including user preferences,
general knowledge, and contextual data. This repository supports personalized responses by
allowing the AI Agent to recall relevant information based on the user's history and
preferences. The Knowledge Base can be updated continuously, ensuring that the AI Agent
remains informed and capable of providing accurate and relevant information.
Learning Engine
The Learning Engine applies machine learning techniques to improve the AI Agent's
performance over time. By analyzing user interactions and feedback, the Learning Engine
adapts the AI Agent's responses and functionalities to better meet user needs. This continual
learning process is essential for enhancing the system's effectiveness and ensuring that it
evolves alongside user preferences and behaviors.
Response Generator
The Response Generator crafts meaningful and natural language responses to user queries,
completing the interaction cycle. It utilizes templates or generative models to produce
coherent replies that align with the user's intent and the context of the conversation. A well
18
19
Chapter 5: Implementation
5.1 Purpose
The implementation phase is a critical step in the development of the AI Agent, where the
theoretical design and planning are transformed into a functional system. The primary
purpose of this phase is to develop and integrate the various software components and
algorithms that enable the AI Agent to effectively understand user input, process that input,
and deliver appropriate responses or actions.
Development of Core Functionalities:
During implementation, programming languages such as Python are utilized, along with
powerful machine learning libraries and frameworks like TensorFlow and NLTK. These tools
are essential for building the core functionalities of the AI Agent, including natural language
processing, dialogue management, and response generation. Each of these components is
coded to perform specific tasks that contribute to the overall functionality of the AI Agent.
Modular Development and Testing:
The system is divided into different modules, each responsible for a specific function. This
modular approach allows for individual coding and testing of each component, ensuring that
they work correctly before integration. Rigorous testing is performed to verify that the AI
Agent can handle various scenarios accurately, manage user data securely, and provide a
satisfactory user experience. This phase is crucial for validating the feasibility of the design in
practice and identifying any issues or limitations that must be addressed.
Deployment and Data Management:
Once the components are developed and tested, the AI Agent is deployed on a server or cloud
platform, making it accessible to end-users. Additionally, databases are set up to manage
interaction
logs and learning history, which are vital for the AI Agent's ability to learn and adapt over
time. The ultimate goal of this implementation phase is to create a reliable, efficient, and
scalable AI system that meets the objectives defined in earlier chapters.
20
5.2 Modules
To streamline the development process, the AI Agent system is organized into modular
components, each responsible for a specific function. This modular architecture facilitates
easier development, troubleshooting, and future upgrades.
Input Processing Module
The Input Processing Module is responsible for capturing and cleansing user input. It
converts natural language into a structured form that can be easily analyzed. Key tasks
performed by this module include:
Tokenization: Breaking down the input text into individual words or phrases.
Part-of-Speech Tagging: Identifying the grammatical roles of words (e.g., nouns, verbs) to
understand sentence structure.
Syntax Parsing: Analyzing the grammatical structure of sentences to derive meaning.
By preparing the data in this way, the Input Processing Module ensures that subsequent
modules
can perform deeper semantic analysis effectively.
Intent Recognition Module
The Intent Recognition Module utilizes machine learning classifiers to identify the user’s
intent behind a query. This module is crucial for understanding what the user wants to
achieve, whether it’s scheduling a reminder, searching for information, or performing another
action. It is trained on labeled datasets to improve accuracy and can adapt to new intents as
more data becomes available. This capability is essential for providing relevant and timely
responses to user requests.
21
Task Execution Module
Once the intent is identified, the Task Execution Module carries out the requested task. This
module interfaces with various APIs, such as calendar services or information databases, to
manage scheduling, retrieval, updates, and notifications. For example, if a user requests to set
a reminder, this module will interact with the calendar API to create the event. The Task
Execution Module ensures that the AI Agent can perform practical actions based on user
input, bridging the gap between understanding and execution.
Learning Module
The Learning Module serves as the AI Agent’s adaptive component. It employs techniques
such as reinforcement learning or supervised learning to refine its understanding of user
preferences and improve future responses based on interaction outcomes. By analyzing user
feedback and behavior, this module helps the AI Agent evolve over time, ensuring that it
becomes more effective and personalized in its interactions.
Response Generation Module
The Response Generation Module is responsible for converting system decisions into human-
readable replies. It utilizes either template-based approaches or generative language models
to produce coherent, context-aware responses. This module ensures that the AI Agent
communicates effectively with users, providing answers that are not only accurate but also
natural and engaging.
Data Management Module
The Data Management Module is tasked with securely storing user profiles, conversation
histories, and AI model parameters. It plays a critical role in ensuring data privacy and
efficient access to historical data, which is essential for improved personalization. By
managing user data responsibly, this module helps build trust with users and enhances the
overall experience by allowing the AI Agent to recall past interactions and preferences.
22
23
Chapter 7: Conclusions
1. Summary of Project Achievements
The AI Agent project has successfully developed an intelligent system capable of interacting
naturally with users and assisting them in managing daily tasks. The system integrates
advanced artificial intelligence techniques, including machine learning and natural language
processing, to understand user queries, automate routine activities like scheduling, and
personalize responses based on individual preferences.
Through modular architecture, the AI Agent can process inputs, recognize user intents,
execute tasks, learn from interactions, and generate human-like replies. These capabilities
demonstrate that the project’s objectives, as outlined in the initial chapters, have been met
effectively and have delivered a functional and scalable AI solution.
2. Improvement Over Existing Systems
Compared to popular virtual assistants currently available, the designed AI Agent shows
significant enhancements in contextual understanding and personalization. While many
existing systems respond only to predefined commands or basic requests, this AI Agent
dynamically adapts based on interaction history and user preferences.
Its support for multi-turn conversations and more sophisticated task handling allows it to
deliver a richer and more user-centric experience. This improvement addresses some critical
limitations found in current commercial assistants, making the agent a valuable advancement
in AI-driven personal assistance.
3. Challenges Faced and How They Were Addressed
During the development of the AI Agent, several challenges arose. One major obstacle was
handling ambiguous or context-dependent user inputs, which required designing robust
natural language understanding modules and carefully curated training datasets. Another
challenge was ensuring data privacy and security while maintaining efficient access to user
data.
24
These challenges were addressed by implementing advanced NLP models capable of
semantic analysis, deploying rigorous data encryption methods, and adopting a modular
design that supports scalability and security. Additionally, thorough testing helped identify
and resolve issues related to response accuracy and system stability.
4. Potential Future Work
The AI Agent project lays a strong foundation for further enhancements and extensions.
Future work could involve integrating voice recognition capabilities to allow hands-free
interaction, making the agent accessible via mobile and wearable devices.
Expanding language support to cover multiple languages would broaden the user base and
usability. Improving the learning module to incorporate unsupervised and transfer learning
could further enhance personalization and adaptability. Deploying the system on cloud
platforms with containerization would increase scalability and availability for real-time,
multi-user environments.
5. Overall Impact
In conclusion, the AI Agent developed through this project represents a significant step
forward in creating intelligent, adaptable, and user-friendly AI personal assistants. By
successfully combining natural language processing, machine learning, and modular system
design, the project demonstrates how AI can be leveraged to improve user productivity and
satisfaction.
Its adaptability and learning capabilities promise more meaningful human-computer
interactions and set the stage for advanced AI systems that seamlessly integrate into everyday
life. This project contributes not only to academic fulfillment but also to practical
applications with the potential for real-world impact.
25
Chapter 8: References
1. Importance of References
References are a critical component of any academic or professional project. They serve
several important purposes:
Credibility: Citing reputable sources enhances the credibility of your work. It shows that
your project is grounded in established research and practices, which can help build trust with
your audience.
Acknowledgment: References give credit to the original authors and researchers whose work
has influenced your project. This acknowledgment is essential in academic and professional
settings to respect intellectual property rights.
Resource for Further Reading: By providing a list of references, you offer readers the
opportunity to explore the topics discussed in your project further. This can lead to a deeper
understanding of the subject matter and encourage continued learning.
Avoiding Plagiarism: Properly citing sources helps avoid plagiarism, which is the unethical
practice of using someone else's work without giving appropriate credit. This is crucial for
maintaining academic integrity.
26
Fig No.1 - Type of AI Agent
27
Fig No.2 - AI Decision – Making Framework
28
