Master in Generative Artificial Intelligence

The first topic provides context on the origins of artificial intelligence, the initial challenges it faced, and its evolution to the present day. It also examines the future prospects of this technology.

Definition and concept of AI History and evolution of AI Fields of AI

The business landscape of AI International adoption statistics and metrics The future of AI

A detailed explanation of how the technology works is provided, making it possible to understand the possibilities and limitations of generative AI, including knowledge of the architecture of generative AI models.

Introduction to generative deep learning Word embeddings Autoencoders: Word2Vec (CBOW and Skip-gram) Recurrent Neural Networks: LSTM and GRU

Keras Transformers Generative Adversarial Networks (GANs)

In this topic, students will learn to design effective prompts for AI systems. Advanced techniques will be explained to maximize the quality and coherence of the responses generated. They will also study the role a prompt engineer plays in configuring and designing a new solution based on generative AI. They will understand how to configure the data capsule that must be sent to the model, along with the user's input, so that the resulting output is adapted to the corresponding use case. Upon completing this module, students will be equipped to design prompts that optimally guide the generation of responses in generative AI systems. 

Introduction to prompt engineering Effective prompt design Best practices in prompt engineering Priming as a prompt engineering technique Zero-shot prompting, one-shot prompting, and few-shot prompting Chain-of-thought and zero-shot chain-of-thought techniques

Role playing technique, limitations, and jailbreaking Generated knowledge prompting and knowledge integration Few-shot CoT and self-consistency techniques Comparative prompting technique Tools and resources for prompt engineering

Generative artificial intelligence has radically transformed the creation of text and valuable information. Thanks to it, this process can be automated to generate content that, in many cases, surpasses human-written material in quality and efficiency. However, to take full advantage of its potential, it is essential to learn how to use this technology correctly and how to optimize its results.
In this topic, we will explore the most advanced solutions in content generation, analyze their practical applications, and learn how to get the most out of the most relevant tools and models, adapting them to different use cases.

Leading models: GPT, Gemini, Claude, Grok, DeepSeek, Qwen, etc. Case studies on the main applications AI automation in customer service assistants Creating custom GPTs and agents in Google Colab

Extracting structured information Using NotebookLM Implementing internal Q&A for information retrieval RAG for personalizing AI with external or proprietary sources

This topic focuses on using generative AI to analyze data and automate report creation. Students will learn to interpret large volumes of information using tools such as Claude for analysis, structuring, and drawing conclusions, along with Power BI for visualization and dashboard creation, and Perplexity to research, cross-check, and validate data with reliable sources, turning information into clear, actionable, and visually compelling reports.

Introduction to generative AI in data analysis Data analysis and drawing conclusions with Claude Research and data validation with reliable sources (Perplexity)

Automatic report generation with AI Data visualization and dashboard creation (Power BI) Case studies across different sectors

Generative AI has revolutionized the creation of images and graphic design by enabling the automated generation of visual content. Through deep learning algorithms, this technology analyzes and understands patterns and features in image datasets in order to generate new, original images. Generative image AI has applications in a wide range of fields, including graphic design, advertising, the entertainment industry, and scientific research. In this module, students will learn to efficiently use the most powerful models and tools currently available for generating and editing graphic content. In addition, they will build the foundations needed to create innovative solutions that leverage these tools and models across various professional areas.

Features and how it works Available technology frameworks (models) Best free tools Best paid tools Creating and editing images

Application possibilities and limitations Automating and optimizing processes that involve images Innovation and the creation of new solutions Hands-on practice with tools

In the specific field of audio, generative AI has proven its usefulness across a range of areas. One of the most notable applications is voice synthesis, which consists of creating synthetic voices that are increasingly natural and realistic. These voices are used in automated response systems, virtual assistants, audiobook narration, and even in the entertainment industry. AI's ability to generate synthetic voices with human-level quality is transforming the way we interact with technology and consume audio content. In this case, you will learn to make efficient use of today's most powerful models and tools specific to voice and sound generation, and you will also lay the groundwork for creating innovative solutions that take advantage of these tools and models.

Features and how it works Available technology frameworks (models) Best free tools Best paid tools Voice and sound creation

Application possibilities and limitations Automating and optimizing processes that require voice or sound Innovation and the creation of new solutions Hands-on practice with tools

Generative AI has revolutionized video creation by enabling the automated generation of original content. This technology uses advanced algorithms to create new, personalized videos from training data. Some notable applications include animation, special effects, and the enhancement of existing videos. Generative AI for video opens up new creative possibilities and transforms how visual content is produced and consumed. This topic covers the efficient use of the most powerful models and tools for video generation and editing, laying the groundwork for innovative solutions that take advantage of these tools and technology frameworks.

Features and how it works Available technology frameworks (models) Best free tools Best paid tools Video creation and editing

Application possibilities and limitations Automating and optimizing processes that involve video Innovation and creation of new solutions Hands-on practice with tools

In this topic you will learn the fundamentals of vibe coding, an approach that lets you create software through natural language instructions, with no technical programming knowledge required. Using Claude, you will turn ideas into functional digital products quickly and intuitively.

Vibe coding for building websites Vibe coding for building applications Vibe coding for building intelligent agents MCP and connecting external tools

Skills and creating new capabilities Visual iteration and prototyping with AI Building digital products with no code Kimi K3 as an alternative to Claude for AI-assisted development

In this topic you will learn to use Claude to automate interaction with your computer through AI agents capable of replicating human behavior. Artificial intelligence will be able to move the cursor, type, browse, and operate desktop and web applications, carrying out work tasks autonomously.

Automating web browsing Automating interaction with web applications Automating desktop programs

Controlling the computer from mobile devices Chrome extension for automating interaction with the computer Integration with agents and workflows

The integration of Generative Artificial Intelligence into everyday work tools is transforming the way professionals manage their time and resources.
This topic shows how to leverage these technologies to improve productivity and efficiency at work, optimizing everyday tasks such as drafting documents, creating presentations, managing email, and organizing meetings and calendars.
The goal is for students to learn to incorporate AI-based solutions into their professional day-to-day work, understanding both their potential and their limitations.

Best free and paid tools Integration with office software Real use cases in workplace settings Implementation strategies Application possibilities and limitations

Microsoft 365 Copilot Gamma: automatic generation of professional presentations. Otter.ai and Fireflies: automatic transcription and summarization of meetings. Intelligent solutions for managing email and calendars.

This topic focuses on integrating technologies to automate processes within organizations. In this module, participants will learn to create automated workflows with Make and then integrate generative AI into those workflows to improve the efficiency and effectiveness of their automations. Other advanced automation technologies will also be explored so that students become familiar with the different options available on the market for a variety of business needs.  This topic will also serve as the conceptual and practical foundation for the sessions on n8n, covered later on. 

The context of process automation The potential of generative AI in the context of process automation Workflow automation with Make

Integrating generative AI into workflows Other automation technologies Make

This module focuses on the concept of Agentic AI, which refers to artificial intelligence systems capable of acting autonomously to automate complex problems. Students will explore how to design and build these agents, which can be customized to each use case, and how to apply protocols such as the Model Context Protocol (MCP) to improve their efficiency. The topic takes an eminently practical approach, using a range of cutting-edge tools for creating and managing agents: Genspark, Manus, AgenKit, Opal, and n8n, allowing students to experiment with different environments and technologies within today's autonomous artificial intelligence ecosystem. 

Genspark AI Manus AI OpenAI's AgenKit Google's Opal n8n Definition and characteristics of Agentic AI

Architecture and components of autonomous agents Practical applications across different industries Model Context Protocol (MCP) Automatic creation of complete workflows with vibe coding Connecting agents to external knowledge bases with Obsidian Building n8n automations and agents with Claude Code via MCP

This topic examines conversational agents, one of the most widespread applications of modern artificial intelligence. It covers how chatbots and intelligent voice assistants are transforming customer service, technical support, and the automation of communication processes. The approach is practical and applied, combining technical fundamentals with current tools to build and deploy chatbots and voice assistants capable of holding natural conversations, recognizing intents, and managing complex contexts. 

It also reviews advances in automated phone support and integrations with CRM systems.

Optimization and personalization with AI agents NLU (Natural Language Understanding) NLG (Natural Language Generation)

Dialogue and knowledge management Development and integration of conversational agents

The AI agent is ceasing to be something you talk to and becoming something that works while you do something else: it monitors, decides, and notifies you only when it truly matters.

In this masterclass we will analyze Hermes live, an agent that runs locally and represents a type of automation different from the ones you already know: it is not triggered by an event like a Make or n8n workflow, nor does it require you to be present as a conversational assistant would. It stays on standby, remembers context between runs, makes decisions about ambiguous information, and learns what you teach it.

Through hands-on demonstrations, students will see how an agent of this kind is built, how to assign it a background task, and how to have it notify you only about what requires attention.

 In this module, participants will learn how to use and configure existing generative AI models to create their own projects and tools. They will understand how to install or connect to the leading generative AI models and technologies in order to build solutions that incorporate these technological foundations and adapt them to their specific needs. 

The module also covers deploying generative AI models on in-house infrastructure, both physical and in the cloud, for environments that require secure handling of sensitive information. Finally, students will discover how to build tools and projects using no code and low code approaches, allowing them to create effective solutions without prior programming knowledge. 

Connecting and integrating with the leading generative AI frameworks (models) and technologies Risks associated with calls to external infrastructure Available APIs In-house infrastructure for implementing AI solutions

Physical infrastructure Cloud infrastructure: AWS, GCP, Azure, IBM Building tools with no code Building advanced tools with low code (no prior programming knowledge required)

This topic analyzes how companies can leverage generative AI to optimize processes, reduce costs, and improve decision-making. It examines the main AI models available and the key factors to consider before launching a project, such as data, technology, and talent.  It also explains how to apply generative AI in leading sectors such as banking and insurance, telecommunications, retail, health, pharma, and legal, exploring specific applications and highlighting how AI is transforming each of these industries. 

Generative AI models and their applications The impact of AI across different sectors Process automation and optimization Personalization of products and services

Cost reduction with generative AI Revenue growth through generative AI Challenges in AI adoption Key benefits for business productivity

The browser is no longer a simple window to the internet; it is becoming an agent that researches, decides, and acts on your behalf.

In this masterclass we will analyze live the agentic browsers leading this transformation, each with a different approach: one specialized in research and information synthesis, another in the autonomous execution of complete tasks, and a third case that illustrates how quickly this market is evolving.

Through hands-on demonstrations, students will see how these tools work, how they differ, and what limitations they still have.

To design any generative AI solution correctly, it is essential to take into account the regulations and laws governing its use. The goal is to ensure that solutions comply with all regulations and avoid potential regulatory problems and litigation. In addition, this topic explores the ethical aspects that are fundamental to the field of AI. By the end, students will be prepared to address the ethical and regulatory challenges posed by AI, contributing responsibly to the development of this technology.

Legal framework and regulations for AI Regulations to consider when designing generative AI projects Sector-specific regulations

Key ethical aspects of artificial intelligence Accountability and governance in AI The future of ethics and legislation in AI

This module focuses on how to apply generative AI in established companies. It analyzes existing business models and identifies opportunities for improvement through the use of generative AI. Students will learn the specific considerations for implementing this technology effectively. The module also explores the role of the generative AI consultant, preparing participants to offer this type of service to third parties, as well as process automation. Through examples and simulated cases, participants will gain a practical understanding that will enable them to design new generative AI-based solutions to improve processes and services. By the end, students will have acquired the tools they need to implement generative AI solutions that drive growth and innovation in established companies.

Analysis of existing processes and operations Identifying opportunities for operational improvement Identifying opportunities and add-ons for existing business lines Analysis of opportunities for new products and business lines Designing new business lines for established companies

Functional design of generative AI solutions Specific considerations for implementing generative AI in companies Generative AI consulting Process automation Examples and practical cases

This topic explores how to combine entrepreneurship and generative AI to develop innovative value propositions. Students will learn to conceptualize and validate new business ideas, as well as to identify opportunities in various markets. It also covers the development of a business model canvas and the functional design of generative AI solutions. In addition, it examines the strategic perspective of incorporating generative AI into business models in order to make the most of its disruptive potential. Success and failure cases of startups related to this technology will be analyzed to reinforce best practices, avoid mistakes, and better understand the challenges in this field. By the end of the topic, students will have the knowledge they need to start a venture and design innovative solutions that use generative AI as a key element.

Conceptualizing and validating business ideas Identifying opportunities in different markets Developing a Business Model Canvas

Strategic vision of generative AI for new businesses Functional design of generative AI solutions Case studies of success and failure in startups and generative AI

Building an application with AI is only the first step. The real challenge begins when that idea has to survive outside your computer: with real data, real users, and an address anyone can visit.

In this masterclass we will take that leap with Claude Code: we will build a complete application live, from start to finish, with a database and real deployment, also incorporating agentic automation into the workflow itself. You will see how far you can go today without writing code, and you will clearly understand where that territory ends and the work of a technical team begins.

A hands-on session to get over your fear of the word "production" and learn to navigate it with sound judgment.

In this module, students will learn how to effectively plan and lead projects in the field of generative AI. It covers how to define project management objectives, the key roles within an AI team, the resources required, their costs, and other relevant aspects. The different phases of an AI project's life cycle will also be explored, along with agile methodologies adapted to this context. In addition, students will develop skills in risk management and in the measurement and evaluation of AI projects. This module will give students the competencies needed to successfully plan, lead, and evaluate generative AI projects.

Definition and objectives of AI project management Roles within an AI team Project architecture Required resources Cost calculation and budgeting Financial assessment of projects

Phases of the AI project life cycle Project planning Project management and implementation Agile methodologies Risk management in AI projects Project metrics and evaluation

In this chapter, everything learned will be put into practice through the simulation of real cases that students will encounter in their professional careers. On one hand, real business situations are presented with new opportunities for improvement thanks to generative AI. On the other hand, students will work on cases in which certain needs can be met by creating new applications or tools based on this technology. Students will have to design optimal solutions for different types of organizations or users by applying generative AI. Classes will include debates to examine the different possibilities and find, with the instructor's help, the best functional options. Active participation in these debates will be key to consolidating knowledge. Students must read the case descriptions and prepare them before the in-person debate sessions.

Before the master concludes, the main advances and developments from the months preceding this module will be introduced, so that students finish with a fully up-to-date profile and understand how quickly the field of generative AI is evolving.