Master in Automation Engineering with Agentic AI

If you have no prior experience with Python, you will have access to a leveling prework designed to give you the necessary foundations before starting the master. You will learn the fundamentals of the language through practical, dynamic, self-correcting content, and you will be able to earn the official IT Specialist Python (ITS-303) certification. 

Introduction to programming Introduction to Python Data types Variables Basic input and output operations Basic operators Boolean values Conditional execution

Loops Bitwise operations Lists Functions Tuples and dictionaries Exceptions

This topic introduces modern automation and the role of generative AI in business environments. It examines the shift from scripting and RPA toward systems based on models, APIs, and agents. It also covers the generative ecosystem and the practical setup of the technical working environment for AI projects. 

The evolution of automation​ Identifying automatable processes​ The generative AI ecosystem​ Capabilities and limits

Automation use cases with generative AI Generative models (text, image, audio)​ Setting up ​work environments Introduction to Git Troubleshooting the environment​ Hardware requirements

This topic presents the fundamentals of machine learning and deep learning, as well as the conceptual foundations of language models. It explains the principles of training, inference, and practical use of models in business and automation contexts.

Introduction to machine learning​ Fundamentals of deep learning​ and neural networks Deep learning libraries: PyTorch Lightning, Tensorflow Transformers​ NLP Generative diffusion and its principles Technical introduction to generative AI​ Introduction to LLMs

Model learning​ Types of models: discriminative, generative, autoregressive Supervised vs. unsupervised models Prompting and inference​ Business uses​ Limits and risks​

Most modern automation relies on integration between digital services through APIs. This module teaches how to build robust automations that connect platforms, services, and applications programmatically. It covers common patterns in enterprise integrations, authentication management, error handling, and event-based automation. Students will learn to design integrations that automate complete processes across multiple systems.

Consuming REST APIs from Python​ Authentication with tokens, OAuth, and API keys​ Managing pagination, rate limits, and errors in integrations​ Designing automations across multiple digital services​

Event-based automation and the use of webhooks​ Developing scripts for enterprise integrations​ Introduction to Postman Structuring system-to-system integration projects​ Designing automated data exchange pipelines​ Connecting APIs with frontends and monitoring Using image generation APIs from Python

This module focuses on the practical use of generative models through APIs. Students will learn to integrate artificial intelligence capabilities into automated systems using the SDKs and APIs available on the leading AI platforms. It covers aspects such as context management, call optimization, cost control, and the design of applications that use models as components within a larger system. Students will work with prompt engineering techniques to design effective instructions.​

Integrating generative models through APIs from Python​ Using APIs with Postman and creating your own APIs (FastAPI, Flask) Designing applications based on models as a service​ Managing context and conversation in model calls​ Applying prompt engineering techniques for automation​ Optimizing token usage and controlling operating costs​

Implementing response streaming in applications​ Managing errors and latency in model calls​ Designing automated pipelines with AI integration​ MLOps: lifecycle, updates, monitoring, and maintenance​ Observability in systems based on AI models ​CI/CD, containers (Docker), microservices, and orchestration Deployment strategies (canary, blue-green) and autoscaling

Enterprise applications require models to access information specific to the organization. This module introduces Retrieval Augmented Generation (RAG) techniques, which connect generative models with knowledge bases, documents, and corporate data. Students will learn how to build systems that combine information retrieval and text generation to create assistants capable of working with specialized knowledge.

Vector spaces: basic concepts and distance calculation Fundamentals of RAG architectures​ How embeddings work Generating and using embeddings for semantic retrieval​ Building vector databases ​ Designing document indexing pipelines​

Using LangChain and LangGraph in retrieval systems​ Integrating embeddings and LLMs: RAG, best practices, and optimizers Evaluating quality and relevance in semantic search systems​ Developing assistants based on specialized knowledge​

In this topic, students will learn to design and build tools and automation processes ready for use by AI agents. It covers integration principles, function definition, workflow structuring, and development best practices. It also introduces the MCP protocol as a mechanism for connecting agents with intelligent tools, making it possible to orchestrate tasks, exchange data, and scale automated solutions securely, efficiently, and flexibly across today's global business and technology contexts.​

Use of external tools by AI models​ Developing tools for AI agents​ Integration with automation frameworks and libraries​ Implementing internet search in AI agents​

Automated code execution in AI systems​ Implementing the Model Context Protocol (MCP) Document processing: from OCR to vision models​ Evaluating integration frameworks and libraries​

The goal of this topic is to learn how to use the leading open source generative AI models and explore the current ecosystem, understanding their characteristics, differences, and use cases. Students will learn to install, configure, and run models in local environments, assessing performance, costs, and privacy. They will work with tools and workflows that make it possible to integrate these models into real applications, building technical autonomy and the ability to deploy AI solutions without depending on external infrastructure.​

Introduction to the open source AI model ecosystem​ Installing and running models in local environments​ Using Ollama to manage local models​ Using Hugging Face to download and manage models​

Comparing performance, costs, and hardware requirements​ Best practices in data management and privacy​ Experimenting with models in NLP, vision, and audio tasks​

This module introduces one of the most significant approaches in the recent evolution of automation: agent-based systems. Students will study how generative models can act as components capable of planning tasks, using tools, and managing complex processes. They will also learn to design agent architectures able to coordinate the processes covered so far, building intelligent systems that execute automated tasks using APIs, data, and external services.​

Architecture of agent-based systems​ Designing agents that use tools and external APIs​ Implementing task planning and execution mechanisms​ Managing memory and context in agents​

Designing multi-agent systems for complex tasks​ Using agents and assistants with ReAct prompting Integrating agents into enterprise automation workflows​

This topic covers the continuous evaluation of AI agents to ensure they act reliably, safely, and in line with the defined objectives. Students will learn to measure their performance, detect unexpected behaviors, apply guardrails, monitor tool use, and establish observability, human control, and continuous improvement mechanisms.

Defining quality, reliability, latency, and availability metrics Assessing goal achievement and task execution Designing tests, scenarios, and benchmarks for agents Detecting hallucinations, errors, and unexpected behaviors Implementing guardrails and validating inputs and outputs

Protection against prompt injection, tool abuse, and data leaks Permission management and applying the principle of least privilege Observability through logs, metrics, traces, and audit records Incorporating human oversight and approval mechanisms Red teaming, incident analysis, and continuous improvement of agents

In this topic, students will learn to design and develop conversational agents capable of interacting in real time, both via chat and through phone calls or voice. It covers speech synthesis and recognition techniques, as well as integration with communication platforms. Students will explore conversation flows, context handling, and best practices for creating smooth, natural experiences, preparing agents that can assist, inform, and serve users autonomously and efficiently​

Designing conversational agents for chat and voice​ Implementing recognition and synthesis Managing contexts and conversational flows​ Integration with real-time communication platforms​ Optimizing responses for natural interaction​

Evaluating conversational agent performance​ Best practices in automated customer service and user experience​

Automating real processes requires coordinating multiple services, models, and tools. This module covers the orchestration of complex workflows that integrate different technological components. Students will learn to design pipelines that combine API-based automation, AI agents, and data processing within robust, maintainable architectures.

Designing multiservice automation workflows Implementing data pipelines and automated processing​ Managing dependencies and task execution​ Designing event-based automation​

Implementing queue systems and asynchronous processing​ Monitoring and debugging automation pipelines​ Designing scalable automation architectures​ Multi-agent systems. Agent orchestration

Many enterprise platforms are used through web interfaces. This module teaches how to automate interaction with web applications using browser automation tools. Students will learn to build bots capable of navigating sites, interacting with forms, extracting information, and running automated processes on online platforms.

Browser automation using modern frameworks​ Interacting with dynamic elements in web applications​ Automating forms and complex navigation flows​ Extracting structured data from web pages​

Designing bots to interact with online services​ Managing sessions, authentication, and cookies​ Integrating web automation into process pipelines​

This topic introduces AI-assisted software development through vibe coding methodologies. Students will learn to turn requirements into working applications, use Claude Code throughout the entire development cycle, and automate code planning, generation, review, testing, and deployment tasks while maintaining quality, security, and traceability criteria.

Fundamentals and methodology of vibe coding Turning requirements into technical specifications Planning applications with AI assistants Generating and refactoring code with Claude Building frontend, backend, and databases

Debugging and assisted error resolution Generating tests and technical documentation Reviewing quality, security, and maintainability Integration with Git and version control workflows Automating application development and deployment

Design an application from scratch alongside Claude Code: architecture, interface, backend, database, testing, and security. You will learn to turn requirements into working code, automate the development workflow, and deploy the product to production through a reproducible, fast pipeline ready to keep evolving.

Claude Code: code planning, generation, refactoring, and debugging. Git and GitHub: version control and professional project management. Frontend, backend, and database: building the application end to end.

Testing, security, and quality: automated validations, review and error resolution, guardrails, and security. CI/CD and deployment: automation with GitHub Actions and publishing to the cloud.

This module covers the use of Python as an orchestration language for automation systems. It goes in depth into development patterns used in real projects, including project structuring, error handling, logging, system task automation, and building robust scripts. The goal is for participants to be able to develop maintainable automations ready for production environments.​

Designing structured automation projects in Python​ Implementing logging and monitoring in automated scripts​ Error handling and retries in automated processes​ Automating operating system tasks from Python​

Implementing scheduled jobs and recurring processes​ Building reusable tools for automation​ Integrating automation scripts into larger pipelines Testing and QA of generative applications

This topic covers the design and use of personal agents capable of executing tasks, using tools, and automating processes autonomously. Students will learn to configure OpenClaw and Hermes Agent, manage memory and permissions, integrate external services, and deploy supervised, observable agents adapted to personal and professional needs.

Architecture and operation of personal agents Installing and configuring OpenClaw and Hermes Agent Defining goals, instructions, and agent profiles Integration with tools, APIs, and external services Managing memory, context, and persistent knowledge Automating recurring tasks and personal processes

Planning, executing, and tracking actions Configuring permissions, limits, and guardrails Human oversight and approval of sensitive operations Monitoring, auditing, and error resolution Deploying and maintaining personal agents in production

Design an SRE agent capable of receiving alerts, investigating metrics and logs, identifying the root cause of an incident, generating a fix, validating the code, and deploying it in a controlled way. You will build a complete workflow with human oversight, operational memory, observability, canary deployments, and automatic rollback.

Hermes Agent and tool calling: planning, autonomous execution, and coordination of the resolution process. OpenTelemetry, Prometheus, and Grafana: anomaly detection and analysis of metrics, traces, and logs. GitHub and CI/CD: patch generation, automated tests, pull request, and human approval.

Docker and Kubernetes: canary deployment, production validation, and rollback on errors. Memory and guardrails: incident history, permissions, action limits, and full auditing.

In this unit, students will learn to deploy intelligent automation systems in local environments, controlling infrastructure, security, and performance. It covers the installation, configuration, and orchestration of AI agents, tools, and services, as well as the integration of automated workflows into the company or personal projects. Students will gain the skills to independently operate complete automation systems, maximizing efficiency, privacy, and scalability without depending on cloud services.​

Installing and configuring automation systems in local environments​ Deploying intelligent agents and associated tools​ Orchestrating automated flows in controlled environments​ Monitoring system performance and security​

Managing dependencies and updates in local environments​ Building frontends with Gradio and Streamlit​ Integrating APIs with frontends and monitoring​ Cost and performance assessment​ Optimizing systems for efficiency and scalability​

Deploying automation systems requires infrastructures capable of running workflows, agents, and AI services at scale. This module introduces the principles of using the cloud to deploy automation solutions. It covers computing services, containers, serverless, and event-based architectures that make it possible to operate automated systems in production environments.​

Introduction to general cloud use and cloud computing tests Data storage and management in the cloud (vectorstores) Security and authentication (API keys, endpoint protection) Designing automation architectures in the cloud​ Deploying automation services in containers​ Using serverless functions for automation​

Deploying open source models​ Implementing automation pipelines in cloud environments​ Managing storage and message queues​ Integrating AI services into cloud architectures​ Designing scalable, resilient systems​ Cost and performance evaluation​

This module addresses the legal, regulatory, and governance aspects required to develop automation solutions based on generative AI, including cybersecurity, traceability, and audit practices. Participants will learn to implement secure, responsible systems aligned with current legislation, ensuring data protection, risk control, and regulatory compliance in business environments.​

Legislation applicable to AI and automation​ Identifying legal, ethical, and operational risks​ Applying cybersecurity practices in automated systems​ Implementing traceability and decision control​

Designing audit mechanisms in pipelines and agents​ Version management and deployment of automations​ Compliance with privacy and data protection regulations​ Cost control and efficiency in the use of AI models