Master in AI Agents and Process Hyperautomation

Introduction to hyperautomation as a driver of digital transformation. It explores enabling technologies, success factors and challenges, illustrating their disruptive impact on business processes through real, cross-industry cases.

Definition and fundamentals of hyperautomation Strategic benefits for the company Real, cross-industry use cases

Main challenges and barriers to adoption Overview of enabling technologies Current and emerging trends

This section examines in depth how intelligent agents work, their practical applications and how to integrate them into the business fabric to improve processes and the customer experience. It explores their capabilities and limitations, as well as the governance aspects of their responsible integration into companies. In addition, generative artificial intelligence is presented as a key paradigm that enables new capabilities in the evolution and behavior of these agents. 

Definition and workings of intelligent agents Differences between cognitive and traditional automation Practical application cases across different industries Tools and platforms for building intelligent agents Impact on productivity and decision-making Agent architectures

Introduction to large language models Key AI tools: ChatGPT, Copilot, Gemini Integration into workflows for automation Automating writing and analysis tasks Model Context Protocol (MCP) Practical application and examples

This section covers the design and optimization of instructions to guide the behavior, reasoning and decision-making of AI agents. It goes into depth on contextual structuring techniques, autonomous reasoning patterns, model parameter control and output validation, and conceptually introduces the integration of internal knowledge bases (RAG) as a technique for reducing hallucinations and improving the accuracy and verifiability of responses.

Clarity, specificity and management of operational context Zero-Shot, One-Shot and Few-Shot Prompting Step-by-step reasoning with Chain of Thought, Self-Consistency and Self-Critique ReAct methodology (Reason + Act) for autonomous agents Modular prompting and Compiler Prompting

Parameter and model temperature tuning Output validation and anti-hallucination techniques Error handling, safeguards and fallbacks Introduction to RAG and Prompt Chaining for integrating proprietary information

This section explores the practical use of generative artificial intelligence tools to create different types of content efficiently and to understand how to incorporate these capabilities into intelligent agents. 

Introduction to generative AI in content creation Benefits and limitations of generative AI tools in a professional setting Generating presentations with AI

Creating images with AI Generating video and audio with AI

In the first sessions of this section, you will explore how to build automation capabilities for intelligent agents using Make (formerly Integromat), a visual low-code platform for designing complex scenarios that allow agents to orchestrate interactions across multiple applications and services. Emphasis will be placed on how to build level 3 agents capable of executing autonomous actions through API integration and level 4 agents that incorporate self-assessment cycles to continuously improve their performance. It will also show how to define clear roles and instructions to enable centralized, efficient decision-making in these advanced agents.  

Autonomous agents Intuitive configuration AI integration Developing autonomous agents with integrated action execution (level 3) Defining role and instructions

Centralized decision-making Interaction with scenarios Implementing continuous improvement and self-assessment cycles in adaptive agents (level 4) Make

This section focuses on using n8n, a low-code, open-source tool, to design automation flows that allow intelligent agents to connect with applications, data and AI services, and to execute tasks autonomously or semi-autonomously. It also covers advanced agents, with the capacity for action, self-assessment, continuous improvement and multimodal processing. 

Modular architectures: planning, reasoning and memory Advanced automation with external systems (level 3 agents) Continuous improvement and self-assessment cycles (level 4)

Vector databases and RAG Agents that combine multiple data modalities Connecting agents to external knowledge bases with Obsidian

This section explores the Claude ecosystem for optimizing productivity and automating workflows on your computer.

Designing advanced prompts, reasoning chains and Few-Shot with Claude Managing continuous context and workspaces with Claude Projects Generating dashboards, interactive documents and forms with Artifacts Creating custom abilities and capabilities through Skills

Web browsing, data extraction and automation with the Chrome extension Desktop agent and autonomous execution of local tasks with Claude Cowork Integrating external tools with MCP Training Skills through screen recording and action logging

Introduction to vibe coding to create functional applications through natural language. This section covers the entire development cycle with Claude Design and Claude Code, from ideation and prototyping to programming, repository management and continuous deployment. It also explores how to take Claude Code beyond traditional software development to build automations, agents and workflows on n8n.

Fundamentals of vibe coding for AI-assisted software development Applying logical, critical and lateral thinking to building software Visual prototyping of interfaces and UI components with Claude Design Exporting and connecting prototypes with design and integration tools Autonomous development and programming from the terminal and web with Claude Code Managing files, repositories and version control with Git and GitHub

Deploying and publishing applications and products on Vercel Creating and editing automations and agents in n8n with Claude Code Creating n8n automations and agents with Claude Code via MCP Integrating software development and low-code automation into a single AI workflow Kimi K3 as an alternative to Claude for AI-assisted development

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

In this masterclass we will make 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 within 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.

Successful automation requires identifying the right processes and analyzing their technical and economic feasibility. This section provides a practical approach to conducting process assessments, analyzing their impact and prioritizing those with the greatest automation potential. It presents clear criteria and tools for selecting the best automation strategies.

Process assessment methods Process mapping tools and techniques Selection criteria for automation

Strategic prioritization Analysis of inefficiencies

The AI agent is shifting from something you talk to into something that works while you do something else: it monitors, decides and notifies you only when it really matters.

In this masterclass we will analyze Hermes live, an agent that runs locally and represents a different type of automation from the ones you already know: it is not triggered by an event like a Make or n8n flow, nor does it require you to be present like a conversational assistant. 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.

From conceptualization to implementation, every automation project requires detailed planning. This topic presents the key phases, the success indicators, and how to present a solid business case that supports the technology investment. It includes practical business case examples and tools for efficient project management.

Key phases of the automation project life cycle Success indicators in projects Cost estimation Presenting a solid business case

Return on investment From conceptualization to implementation Process monitoring Resource and risk management

Mastering BPMN notation is key to defining processes in a standardized way and facilitating their subsequent automation. This topic teaches you how to document workflows precisely, identifying opportunities for improvement and optimization within any functional area. It includes practical exercises using digital tools for process modeling.

Introduction to BPMN and its elements Digital tools for BPMN modeling

Process modeling for automation Identifying improvements and critical points

This topic introduces the fundamentals of robotic process automation with UiPath, an accessible tool for business users. You will learn to create automations that free up time and improve operational productivity.

Introduction to RPA with UiPath How the different types of robots work and how they are applied Creating simple automations

Improving operational productivity Accessible automation for business users Recommended best practices for RPA development

Many business processes depend on handling structured and unstructured information. This topic teaches you how to automate these tasks using data extraction and document automation technologies. Success stories and best practices for developing robust automations are reviewed.

Automating structured and unstructured information Data extraction technologies Document automation

Web scraping for extracting data from websites Business process optimization

As RPA projects scale, ensuring the robustness of solutions is essential. This topic goes deeper into applying ReFramework for error management and building resilient bots.

Designing robust automations Error management with ReFramework Building resilient bots

Scalability of RPA projects Exception handling

Effective enterprise automation requires centralized management of the robots that run digital processes. This topic teaches you how to use UiPath Orchestrator to supervise, scale, and control your automation portfolio.

Using UiPath Orchestrator Robot supervision and control Metrics for monitoring automations

Scaling automations Centralized process management Optimizing the automation portfolio

We explore the use of Power Apps and Power Automate to create low-code applications and automations and integrate them into business processes quickly. 

Low-code automation with PowerApps and PowerAutomate Building applications without technical knowledge Agile solutions for business processes

Integration with enterprise systems Limitations and best practices of low-code solutions

Automating processes that require visual interpretation is possible thanks to computer vision. This topic teaches you how to apply these technologies to extract value from images, forms, and digital documents. Technical challenges are analyzed and advanced application cases across different industries are presented.

Applying computer vision in automation Technical and quality challenges in computer vision Extracting value from images and documents

Visual interpretation for automated processes Using advanced technologies for digital forms Process optimization with visual AI

The browser is no longer just a window onto 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 practical demonstrations, students will see how these tools work, how they differ, and what limitations they still have.

This topic teaches you how to create, deploy, and manage intelligent agents in UiPath, with a special focus on autonomy, orchestration, and collaboration between agents to automate complex business processes. It covers the connection with other enterprise systems, advanced exception handling, and practical cases where several agents cooperate and are monitored from UiPath Orchestrator, seeking efficiency and scalability in professional environments.

Advanced use of UiPath Orchestrator for agent management and deployment Modeling flows where several agents collaborate or share the workload Integrating UiPath agents with APIs and AI systems to expand their autonomy

Agent control and monitoring, exception handling, and scalability Practical cases: end-to-end automation of critical business processes with agents Coordinating teams of agents

Students are trained in the design, development, and integration of virtual and voice assistants. The goal is to enable natural interaction between humans and intelligent systems, covering everything from the principles of conversational design and intent management to implementation on chatbot platforms, integration with enterprise systems, and the exploration of voice technologies. The topic culminates in the practical design of an intelligent virtual assistant, with a focus on invoking automations as "tools" and considering voice interfaces for specific business cases.

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

Dialogue management and knowledge management Development and integration of conversational agents

This topic explores the design, development, and implementation of interactive, personalized avatars powered by artificial intelligence, which can take the form of digital twins, virtual assistants, or characters in immersive environments. Students will learn about the underlying technologies that allow avatars to perceive, understand, reason, communicate, and express emotions, including the integration of generative AI for their appearance, voice, and behavior. Technical, ethical, and human interaction aspects will be addressed, preparing participants to build innovative user experiences across a range of sectors.

Definition of AI avatars: types (digital twins, virtual assistants, characters), purposes, and roles in different contexts Components of an AI avatar: perception (vision, hearing), natural language understanding (NLU), reasoning, generation (NLG, TTS, animation), emotional expression Multimodal interaction: communication through voice, text, facial expressions, and body language

Personalization and adaptation: creating avatars that learn and adapt to the user and the context Visual representation: technologies for creating 3D models, facial and body animation

Students learn to build complex, scalable automation solutions using n8n, communication protocols such as the Model Context Protocol (MCP) and Agent2Agent (A2A), and information retrieval techniques (RAG) to provide agents with up-to-date, traceable context. Work will focus on integrating different systems and orchestrating automated processes in multiplatform environments, always with a hands-on, low-code approach.

RAG fundamentals: architecture, embeddings, and vector databases Best practices and anti-patterns in production RAG systems RAG platforms and enterprise search Features and how they work Differences between architectures Model Context Protocol (MCP)

Agent2Agent (A2A) protocol for horizontal collaboration between agents Hands-on practice with tools Integrating different tools Building complex agents Platforms for generating agents through natural language

The use of AI and automation requires guaranteeing security, regulatory compliance, and data protection. This topic covers current legal frameworks and recommended practices for securing automated solutions. It reviews international regulations and incident response protocols.

Legal and regulatory framework for AI and automation Relevant international regulations. Cybersecurity in automated solutions

Auditing and risk mitigation Ethics and responsible use of AI Best practices for regulatory compliance

Automated decisions must be ethical, transparent, and fair. This topic explores the ethical risks of AI in depth and how to mitigate bias or inequality in the design and use of automated systems. 

Ethics and transparency in automated decisions Mitigating bias and inequality Fair, responsible design of AI systems

Ethical risks in AI Practices for responsible use

This class focuses on the core principles and best practices for the strategic management and planning of automation-centered projects. Participants will learn to define project scope, set clear objectives, identify the resources required, and develop realistic schedules and budgets. It covers the key phases of an automation project from initiation through closing, with an emphasis on risk management and effective communication with stakeholders.

Planning and structure of automation projects Managing resources and teams in projects Cost estimation and Return on Investment (ROI) Budget preparation Project schedule planning

Leadership in automation projects Change management and organizational resistance Maximizing technology adoption Managing processes and people Strategies for project success

This class focuses on applying agile methodologies, such as Scrum and Kanban, to manage projects efficiently, especially those in fast-moving environments such as automation and artificial intelligence. It explores agile principles, roles, ceremonies, and artifacts, preparing students to lead cross-functional teams, adapt to change, and deliver value iteratively and incrementally while fostering collaboration and continuous improvement.

Agile principles and the Agile Manifesto Scrum Framework Applying Agile in automation/AI projects

Tools for Agile management Continuous improvement and adaptability