AI Agents for Everyone & AI Bootcamp with 100 Hands-on Labs

Explore how AI agents learn via supervised learning, reinforcement learning, and imitation learning to gain autonomy, adapt to noisy environments, and generalize to new tasks.

Explore natural language processing for AI agents, enabling intent detection, entity recognition, memory, dialogue management, and language generation with transformer models to power adaptive, multi-turn conversations.

Explore how AI agents become embodied in robotics, bridging sensing and acting through the sensorimotor loop and perception-action cycles, enabling autonomous, safe, real-time decision making in dynamic environments.

Explore open source ai agent frameworks—lang chain, haystack, and open agents—and learn how they handle memory, prompt templating, tool use, and multi-step reasoning for nlp, search, and collaboration.

Discover auto GPT, a system that wraps a powerful LLM to autonomously reason, plan, and act, decomposing goals into subgoals and using tools and memory.

Explore IBM Bee, a modular, governance-driven blueprint for enterprise AI agents that log decisions for auditability, enforce data privacy and compliance, and scale with planner and worker components.

Explore LangGraph for stateful AI agents by modeling workflows as graph-based nodes and edges with persistent memory and finite state machine control.

Coordinate a crew of specialized ai agents with crew ai to assign roles and tools, enabling collaboration, debates, and modular workflows toward shared goals in marketing, analytics, and design.

Deploy AI agents to transform business operations by executing tasks, automating processes, and acting as assistants and analysts, enabling adaptive workflows, intelligent insights, and cross-functional collaboration.

Explore how AI agents augment clinicians in healthcare, supporting diagnosis, trial matching, patient engagement, and workflow automation while upholding privacy, human oversight, and safety.

Discover how ai agents power financial systems with robo advisors, real-time fraud detection, and regulatory compliance, delivering scalable, transparent decision making and faster risk management.

Explore how ai agents revolutionize entertainment through dynamic NPCs, storytelling agents, and creative co-pilots that respond in real time and generate endlessly fresh content.

Explore how AI agents in smart homes and IoT sense context, orchestrate comfort, security, and energy efficiency across devices, creating ambient intelligent experiences with privacy-preserving design.

Explore how future ai agents evolve toward long-horizon autonomy, self-improvement, and memory-driven multimodal, general-purpose reasoning, collaborating across agents to set goals and adapt tools.

Examine fairness, inclusivity, and explainability in autonomous AI agents. Align goals with human values through IEEE ethically aligned design and EU AI act, with audits and diverse oversight.

Navigate data rights, liability, and international regulation for AI agents, including GDPR, CCPA, and emerging laws, and examine accountability across the technology stack.

Explore how AI agents drive productivity gains and workforce displacement while influencing social equity, digital access, and inclusive policy through human plus agent collaboration.

Discover how AI agents collaborate with humans to amplify judgment and creativity, using complementary intelligence and human in the loop design for trusted, efficient workflows.

Discover how AI agents accelerate scientific discovery as autonomous collaborators, powering simulation, lab automation, and hypothesis generation to process vast data, review literature, and accelerate interdisciplinary research.

Explore how AI agents boost public safety and national defense, from disaster response and autonomous drones to predictive policing and cybersecurity, while addressing privacy, consent, bias, oversight, and accountability.

Learn what AI agents are and how they operate autonomously, with hands-on development using Autogen, IBM, Landgraf, crew, AI, and auto GPT frameworks.

Autogen, a Microsoft open-source framework for multi-agent systems, enables agent collaboration, code execution, and tool integration with human in the loop, through a hands-on chat demo.

Explore the IBM Bee agent framework, an open source, model-agnostic platform for modular ai agents, tool integrations, memory management, sandboxed code execution, observability, and multi-agent orchestration under an orchestrator.

Explore Lang Graph, a stateful multi-agent framework in the Lang Chain ecosystem, orchestrating cyclic and branching workflows with large language models and human-in-the-loop control.

Build multi agent ai workflows with crew ai by assigning role-based agents and coordinating sequential, hierarchical, and consensual processes plus tool integrations for content, research, and data analysis.

Auto GPT autonomously manages tasks by defining goals, breaking them into tasks, and iterating with self prompts, using internet research, memory and files management, and plugins.

Explore Python programming basics, from development setup and control flow to functions, modules, data structures, strings, file handling, and pythonic coding practices for week one.

Explore why Python powers AI, cover key libraries for ML, DL, data science, and NLP, and learn end-to-end setup of Python, Jupyter notebooks, and Visual Studio Code for hands-on coding.

Explore Python control flow with if/elif/else, for and while loops, and break and continue, then build prime-checking logic and a menu-driven calculator.

Explore Python functions and modules, learning def, parameters, and return values, and mastering scope and lifetime. Apply modules, imports, and custom scripts to build reusable, modular code.

Explore Python data structures by building and manipulating lists, tuples, dictionaries, and sets; learn indexing, mutability, slicing, adding, removing, and common set operations such as union, intersection, and difference.

Master string manipulation: concatenation, slicing, and f-string formatting, plus split, join, replace, and strip, then use regex with re for pattern matching and text cleaning for NLP.

Learn Python file handling with open, read, readline, readlines, and writelines; count lines and words; and use with statements with robust exception handling.

Develop clean pythonic code with list comprehensions, lambda functions, map, filter, and reduce. Build a command line task manager using os and sys, loading and saving tasks to a file.

Explore week two data science essentials, mastering NumPy for numerical computing, pandas for cleaning, preparation, aggregation, and visualization with matplotlib and seaborn, plus an exploratory data analysis project.

Learn numpy for numerical computing, creating and manipulating arrays, performing elementwise and mathematical operations, and integrating with pandas, matplotlib, TensorFlow, and PyTorch for data science and AI.

Explore advanced numpy operations, including broadcasting, aggregation functions, boolean indexing, and random number generation with seeds, reinforced by hands-on exercises.

Learn pandas for data manipulation by exploring series and data frames, loading and saving csv and excel files, and performing basic operations like head, tail, info, and describe.

Develop clean, analysis-ready datasets with pandas by handling missing values, transforming data, and merging frames to support reliable ai model training.

Master grouping by category in Pandas using group by, iterating over groups, applying mean, sum, and custom aggregations, with pivot tables and hands-on exercises.

Learn to visualize data with matplotlib and seaborn by creating line, bar, scatter, and histogram plots, then explore heat maps and pair plots with customization.

Engage in day seven EDA by applying data cleaning, transformation, aggregation, and filtering to summarize data and uncover patterns, correlations, and insights using matplotlib, seaborn, and pandas.

Explore week three mathematics for machine learning, including linear algebra fundamentals, calculus with derivatives and integrals, optimization, probability and distributions, statistics fundamentals, and a linear regression from scratch project.

Master linear algebra fundamentals by exploring vectors and matrices, performing addition, subtraction, scalar and matrix multiplication, and using NumPy to work with identity, zero, and diagonal matrices.

Explore advanced linear algebra concepts, including determinants, matrix inverses, eigenvalues and eigenvectors, and matrix decomposition via NumPy, with practical Python examples and SVD applications for dimensionality reduction.

Explore derivatives and gradients for machine learning, and apply gradient descent to optimize loss in linear regression with Python and SymPy.

Explore integrals and optimization in machine learning, covering definite and indefinite integrals, probability distributions, local versus global minima, convex and non-convex losses, and SGD variants.

Explore probability theory and distributions, including conditional probability and Bayes theorem, with practical Python demonstrations. Learn Gaussian, Bernoulli, binomial, and Poisson models and visualize them for machine learning applications.

Explore statistics fundamentals, including mean, median, mode, variance, and standard deviation; learn hypothesis testing, confidence intervals, and t-tests, with Python using NumPy and SciPy.

Master linear regression from scratch by implementing the math, applying gradient descent to optimize theta, and evaluating models with mean squared error and R-squared.