Development100% OFF

Agentic AI & Prompt Engineering Bootcamp: Build AI Employees

Udemy Instructor

0(1.1K students)

Self-paced

All Levels

About this course

“This course contains the use of artificial intelligence” Welcome to the AI Engineering Bootcamp: Build, Deploy & Scale AI Agents — a complete, hands-on course designed to take you from beginner to production-level AI engineer.This course is not about just using AI tools. It’s about learning how to build real AI systems, create AI agents, and design AI-powered workflows that work in real-world environments. You’ll start by understanding the fundamentals of Agentic AI and what it truly means to build an AI Employee—a system that can think, act, automate, and operate continuously.We begin with strong foundations in Prompt Engineering, where you’ll learn how LLMs think, how to design high-quality prompts, and how to use frameworks like Role → Task → Context → Output.

You’ll then move into advanced prompting techniques including Chain of Thought (CoT), structured outputs (JSON), and prompt optimization, giving you professional-level control over AI behavior.From there, you’ll set up your environment using tools like Claude Code, understand how to work with APIs, and build your first AI-powered workflow. You’ll then unlock one of the most powerful concepts in AI—memory and context, learning how to create agents that remember users and avoid hallucinations.As you progress, you’ll build your first AI agent architecture, designing systems that process input → logic → output, and adding decision-making capabilities. Then comes the real transformation—creating autonomous workflows that run 24/7 using event-driven systems, cron jobs, and trigger-based automation.You’ll go even deeper by building multi-agent systems, where multiple AI agents collaborate, delegate tasks, and execute workflows like real teams.

Then, you’ll master one of the most in-demand enterprise skills—RAG (Retrieval-Augmented Generation)—allowing your AI to connect with custom data, improve accuracy, and reduce hallucinations.The core of this course is your portfolio-ready projects, where you will build real-world systems including an AI Customer Support Agent, an AI Business Analyst, an AI Email Automation Agent, and a Task Automation Agent. These projects are designed to give you job-ready skills and practical experience.Finally, you’ll learn how to take your systems to production with deployment, VPS setup, and running AI agents 24/7. You’ll also master optimization techniques like cost control, prompt efficiency, caching, performance tuning, and scaling AI systems.To make you a complete AI engineer, the course ends with advanced topics in AI Safety, including handling hallucinations, testing AI outputs, implementing guardrails & validation, debugging workflows, and building monitoring systems for real-world reliability.By the end of this course, you won’t just understand AI—you will be able to design, build, deploy, optimize, and scale production-ready AI systems.

Skills you'll gain

Data ScienceEnglish

Available Coupons

Course Information

Level: All Levels

Suitable for learners at this level

Duration: Self-paced

Total course content

Instructor: Udemy Instructor

Expert course creator

This course includes:

📹Video lectures
📄Downloadable resources
📱Mobile & desktop access
🎓Certificate of completion
♾️Lifetime access

$0$91.99

Save $91.99 today!

Enroll Now - Free

Redirects to Udemy • Limited free enrollments

Share this course

https://freecourse.io/courses/agentic-ai-prompt-engineering-bootcamp-build-ai-employees

Welcome to Building Recommendation Engine with Machine Learning & RAG course. This is a comprehensive project based course where you will learn how to build intelligent recommendation systems using Tensorflow, Surprise and Retrieval Augmented Generation. This course is a perfect combination between Python and machine learning, making it an ideal opportunity to level up your programming skills while improving your technical knowledge in software development. In the introduction session, you will learn the basic fundamentals of recommendation engine, such as getting to know its use cases, technical limitations, and also learn how retrieval augmented generation can be used to improve your recommendation system. Then, in the next section, you will learn step by step how a recommendation engine works. This section covers data collection, data preprocessing, feature selection, model selection, model training, model evaluation, deployment, monitoring, and maintenance. Afterward, you will also learn how to find and download datasets from Kaggle, it is a platform that offers many high quality datasets from various industries. Once everything is ready, we will start the project. Firstly, we are going to build a product recommendation engine using TensorFlow, it will have the capability of suggesting relevant products to users based on their browsing and purchase history. This recommendation engine will be able to analyze user behavior, extract meaningful patterns, and generate personalized product recommendations in real time. By implementing this system, businesses can enhance customer engagement, increase conversion rates, and optimize the shopping experience through intelligent suggestions. In the next section, we are going to build a movie recommendation engine using Surprise, which will help users discover films they might enjoy based on their past ratings and preferences. This recommendation engine will utilize collaborative filtering techniques to find similarities between users and movies, delivering highly personalized recommendations. With this approach, we can improve content discovery, keep users engaged, and drive higher retention rates for streaming platforms. Following that, we are also going to build a music recommendation engine using Retrieval Augmented Generation that is able to provide dynamic and context aware song recommendations. This recommendation engine will be able to enhance traditional recommendation methods by incorporating real-time external knowledge, improving the accuracy and diversity of song suggestions. Lastly, at the end of the course, we will conduct testing to evaluate the performance of our recommendation engines. After ensuring optimal model performance, we will deploy the recommendation system to Hugging Face Space, where users can select a few initial movies as input, allowing the model to process real-time data and generate personalized recommendations based on learned patterns and similarities.Before getting into the course, we need to ask this question to ourselves, why should we build a recommendation engine using machine learning? Well, here is my answer, by leveraging machine learning, businesses can offer smarter, more personalized recommendations that keep customers engaged, increase sales, and improve loyalty. Meanwhile, from users perspective, they can benefit from a seamless experience, where they receive valuable recommendations effortlessly, saving time and effort in finding what suits their needs.Below are things that you can expect to learn from this course:Learn the basic fundamentals of recommendation engine, such as getting to know its use cases, technical limitations, and RAG implementation in recommendation systemLearn how recommendation engines work. This section cover, data collection, preprocessing, feature selection, model training, model evaluation, and deploymentLearn how to download dataset using Kaggle Hub APILearn how to perform feature selection for product recommendation engineLearn how to build product recommendation engine using Tensorflow and KerasLearn how to build product recommendation engine using TFIDF Vectorizer and Cosine SimilarityLearn how to perform feature selection for movie recommendation engineLearn how to build movie recommendation engine using SurpriseLearn how to build and train collaborative filtering modelLearn how to build music recommendation engine using retrieval augmented generationLearn how to load RAG model and create Facebook AI Similarity Search indexLearn how to build search based recommendation engine using RAGLearn how to build user interface for recommendation engine using Gradio and StreamlitLearn how to test and deploy recommendation engine on Hugging Face

AI System Design & MLOps: From Raw Data to AWS Kubernetes

Udemy Instructor

AI System Design & MLOps: From Raw Data to AWS Kubernetes (End-to-End Project)Stop Learning Machine Learning in IsolationMost machine learning courses focus on building models in isolation. You train a model, evaluate accuracy, and consider the job done.But in real-world systems, that is only a small part of the problem.Organizations do not need models. They need systems that can:ingest and process real-world datagenerate reliable predictionsserve those predictions through APIsmonitor performance over timeadapt when data changesThis course is designed to bridge that gap.The Story Behind This CapstoneImagine a large hospital network handling thousands of patients every day.Patients arrive with different conditions. Some cases are routine, while others escalate into high-risk situations requiring immediate attention. At the same time, every visit generates billing records, which are later submitted to insurance providers. Some claims are approved quickly, while others are delayed or rejected, leading to revenue loss and operational inefficiencies.Now consider the questions hospital leadership is asking:Can we identify high-risk patient visits early so that resources can be allocated proactively?Can we predict which claims are likely to be rejected before they are submitted?Can we continuously monitor the system and adapt when patient patterns or insurance behaviors change?These are not just modeling questions. They require a complete, well-designed system.In this course, you will build that system from the ground up.What You Will BuildYou will design and implement a complete healthcare AI platform that includes:1. Data LayerYou will start with raw datasets such as patients, visits, and billing records. Instead of working directly on CSV files, you will create a structured analytics layer using SQL, ensuring that data can be queried, validated, and joined properly.You will then perform exploratory data analysis and build meaningful features such as visit frequency, average length of stay, and provider rejection rates.2. Machine Learning LayerYou will build two real-world models:A visit risk classifier that predicts whether a patient visit is low, medium, or high riskA claim outcome predictor that determines whether a claim will be paid, pending, or rejectedYou will implement multiple algorithms, including Logistic Regression, Random Forest, and XGBoost, and evaluate them using proper metrics such as precision, recall, and F1 score.More importantly, you will understand how data quality impacts model performance and how fixing labels can dramatically improve outcomes.3. MLOps LayerThis is where the system becomes production-ready.You will integrate:MLflow for experiment tracking and model versioningDVC for data versioning and reproducible pipelinesYou will define clear artifacts such as trained models, feature schemas, and prediction logs, ensuring that every step in the pipeline is traceable and repeatable.4. Serving LayerYou will expose your models through a FastAPI-based service with well-defined endpoints for prediction.You will enforce input validation using Pydantic and build a browser-based interface using Gradio for demonstration purposes.You will also implement monitoring mechanisms such as PSI-based drift detection to identify when the system starts behaving differently due to changes in incoming data.5. Cloud Deployment LayerYou will containerize your application using Docker and push images to AWS Elastic Container Registry.You will then deploy the system on AWS EKS using Kubernetes, enabling scalability, high availability, and zero-downtime updates.A complete CI/CD pipeline using GitHub Actions will automate build, test, and deployment steps.6. Continuous Retraining LoopThe system does not stop after deployment.You will implement a feedback loop where:predictions are loggeddrift is detectedretraining is triggered using DVC pipelinesThis ensures that the system continuously improves as new data flows in.How This Course Connects the DotsOne of the biggest challenges in learning AI and machine learning is fragmentation. You learn SQL in one place, modeling in another, APIs somewhere else, and cloud deployment separately.This course connects all of these pieces into a single, coherent system.You will see how:raw data flows into structured analyticsfeatures feed into modelsmodels are tracked and versionedpredictions are served via APIssystems are deployed to the cloudmonitoring drives retrainingBy the end, you will not just understand individual tools. You will understand how they work together.Who This Course Is ForThis course is ideal for:software engineers who want to transition into AI/ML systemsmachine learning practitioners who want to learn production deploymentbackend developers interested in building AI-powered APIsarchitects who want to understand end-to-end AI system designWhat You Will Walk Away WithBy the end of this course, you will have:built a complete end-to-end AI systemdeployed it on AWS using modern cloud practicesimplemented monitoring and retraining mechanismsdeveloped a strong understanding of production-first architectureMore importantly, you will develop the ability to think beyond models and design systems that deliver real business value.Final NoteThis is not a course about isolated concepts. It is about building something that resembles real-world systems.If your goal is to move from learning machine learning to applying it in production, this course is designed for you.Production-first architecture is not an advanced topic. It is the standard.

Data Analytics with Python & AI

Udemy Instructor

Disclaimer: This course contains the use of artificial intelligence(AI).Most data courses teach you Python syntax. This course teaches you how to think like a data analyst, work like a professional, and get hired like one. you will go from writing your first line of Python to deploying a complete data analytics project — with machine learning, AI-powered insights, interactive dashboards, and a GitHub portfolio that proves you can do the work.This is not a theory course. Every lecture has real data, real code, and real business decisions behind it.WHY THIS BOOTCAMP IS DIFFERENTEvery other Python for data course stops at the technical skills. This one goes further. You will learn how to use AI tools like the Anthropic API to analyze data 5x faster, how to communicate insights to executives using the SCQA framework, and how to position yourself for U.S. data analyst roles as an international professional navigating OPT, STEM OPT, and H-1B pathways.The skills in this course are not academic. They are the exact skills hiring managers test in data analyst interviews at U.S. companies right now.WHAT YOU WILL BUILDBy the end of this bootcamp you will have completed a full end-to-end analytics project . Your deliverables will include a clean, documented GitHub repository, a machine learning model that predicts high-value orders with over 80% accuracy, an interactive Plotly Dash dashboard your stakeholders can actually use, an AI-generated executive summary built with the Anthropic API, and an automated Python report that runs and emails itself on a schedule.That portfolio project is your most powerful job application tool. More credible than a certificate. More specific than a resume bullet.WHAT IS COVERED — DAY BY DAYFirst day covers Python foundations built specifically for data work. You will set up your environment, learn the only Python you actually need, and read your first real-world dataset.Day 2 covers data cleaning and wrangling with pandas. You will handle nulls, fix data types, remove duplicates, merge DataFrames, and build an analysis-ready dataset from scratch.Day 3 covers exploratory data analysis. You will apply descriptive statistics correctly, build professional visualizations with Matplotlib and Seaborn, and generate 10 business insights from a real e-commerce dataset without touching a single machine learning model.Day 4 covers AI-assisted analysis. You will make your first API call to a large language model, build a personal analyst assistant in Python, and master prompt engineering techniques specifically designed for data tasks.Day 5 covers machine learning fundamentals. You will build regression and classification models with scikit-learn, interpret every output in plain English, and evaluate your models correctly using cross-validation, confusion matrices, and F1 scores.Day 6 covers dashboards and data storytelling. You will build interactive dashboards with Plotly and Dash, structure analyst presentations using the SCQA framework, and automate a complete reporting pipeline that generates and emails a PDF report on a schedule.Last Day covers your capstone project and career positioning. You will complete a full end-to-end analytics project, publish it on GitHub with a recruiter-ready README, and build a 30-day job search action plan designed specifically for international professionals in the U.S. market.WHO THIS COURSE IS FORThis course is built for international students and professionals on F-1, OPT, or STEM OPT who want to transition into data roles in the U.S. It is also for working professionals in non-technical fields who want to upskill into analytics without a computer science background, and for early-career analysts who know the basics but have never built a complete portfolio project or integrated AI into their workflow.You do not need a mathematics degree. You do not need prior programming experience. You need a laptop, a willingness to write code alongside the lectures, and a goal to land a data role.REQUIREMENTSNo prior Python experience is required. A computer with internet access and at least 8GB of RAM is sufficient. All software used in this course is free and open source. API usage in the AI modules requires a free account — setup is covered in the lecture.A NOTE ON CAREER OUTCOMESData Analyst, Business Intelligence Analyst, Analytics Engineer, and Data Scientist roles are among the most consistent H-1B sponsoring positions in the U.S. market. All qualify for STEM OPT extension under the relevant CIP codes. This course does not just build your technical skills — it builds the portfolio evidence that makes your application stand out to employers who sponsor visas.Every skill in this bootcamp was chosen because it appears in job descriptions, gets tested in interviews, and transfers directly to your first week on the job.Enroll now. Your portfolio project starts in the first lecture.

0.0•6•Self-paced

FREE$97.99

Enroll

Agentic AI & Prompt Engineering Bootcamp: Build AI Employees

About this course

Skills you'll gain

Available Coupons