Agentic AI & Claude Cowork

Context

What if you could delegate your time-consuming tasks to an AI assistant capable of browsing the web, managing your files, drafting your emails, and completing dozens of tasks in just a few minutes—all while you focus on what really matters?

Claude Cowork, launched by Anthropic in 2026, represents a paradigm shift in the way we work. But to fully utilize Cowork, you need to understand what’s happening “under the hood”: how does an AI agent plan? Why does it sometimes fail? How can you give it instructions that actually work? This training answers these questions, moving from concrete examples to concepts, and then back to advanced practical application. This training gives you the keys to start leveraging it immediately.

Assessment and Certification

To complete the training, each participant submits a personalized agent-based AI roadmap: a concrete plan for integrating AI agents into their professional practice, whether at the level of their specific role or their organization.
This assignment provides an opportunity to reinforce what has been learned and to leave with a clear, actionable vision tailored to their real-world context.

Info

Discover the program's assessment and teaching methods  

Participants whose roadmap is approved receive the aivancity “Agent-Based AI & Claude Cowork” Certification. This certification validates a professional certification registered in the Specific Directory (RS) under number RS6787 (registered on October 1, 2024): “ Integrating artificial intelligence and data science into corporate strategy."

Who is this training course intended for?

No technical skills required.

For all professionals who want to take back control of their time. No technical skills required; if you know how to use a computer, you can take this course.

Managers and executives who want to improve their decision-making effectiveness
Consultants and project managers facing ever-increasing volumes of information
HR, marketing, and support functions that handle repetitive, high-value-added tasks

If you manage information, draft documents, coordinate projects, or monitor industry trends, you've come to the right place.

Required equipment: One laptop per participant (Mac or Windows), internet connection, and access to Claude Pro.

Why now?

Agent-based AI is no longer just a promise—it’s an operational reality. Organizations that train their teams today will gain a head start that will be hard to catch up with. In 12 months, the question will no longer be “Should we adopt AI agents?” but “How have you trained your employees?”

2 days of in-person training, 100% hands-on—you’ll work on your own real-world cases, not fictional exercises
Suitable for all skill levels, with built-in differentiated instruction

Objectives

By the end of the training, participants will be able to:

Explain how an AI agent works (perceive–plan–act–observe loop)
Use Claude Cowork independently for their specific business use cases
Build multi-step automation workflows with Cowork
Diagnose and correct unexpected agent behavior
Evaluate and choose among several agent-based tools (Cowork, Operator, Copilot, open-source alternatives)
Identify the risks associated with the use of AI agents in a professional setting

Day 1 - From Discovery to Foundations

Module 1

Cowork in action

Live demonstration of Claude Cowork across various use cases. In just 90 minutes, you’ll see the bot perform tasks that used to take you half a day. The impact is immediate, and the motivation to learn is sparked.

Module 2

Guided First Steps

You’re getting started with Cowork for the first time, step by step. First automation task completed successfully first thing in the morning: research, summarization, formatting. The focus is on confidence, not on completeness.

Module 3

Understanding Agent-Based AI

The core of the training: how an agent plans, makes decisions, and acts. You’ll understand what’s happening “under the hood”—so you can control Cowork with precision and anticipate its limitations, without jargon or math.

Module 4

The Art of Agent-Based Prompting

Giving clear instructions to an agent is a specific skill. You’ll learn about the TASK framework and rewrite your own prompts during the workshop so they’re ready to use right away.

Day 2 - Mastery and Expansion

Module 5

Advanced workflows with Cowork

The entire morning is devoted to hands-on training. You’ll build real-world workflows: information management, communication, reporting, and multi-application integration. Each workshop is tailored to your specific business context.

Module 6

Overview of agent-based tools

Cowork, Operator, Copilot, open-source alternatives… Compare the tools available on the market and create your own decision-making matrix to choose the right solution for your specific needs.

Module 7

Risks, Ethics, and Governance

Having an agent act on your behalf raises serious concerns. You identify the specific risks (data security, GDPR compliance, cascading errors) and work together to develop a responsible use policy for your organization.

Module 8

Action Plan & Conclusion

The training doesn’t end in the classroom. You’ll leave with three workflows to implement starting the following week, a set of ready-to-use resources, and four weeks of post-training support to help you make these practices a lasting habit.

Trainers

Info
Areas of expertise
Management, Management control, Communication and organizational change, Informal control and panoptic control, Governance
Dr. Tawhid CHTIOUI
Professor of Management | Founding President and Dean of Aivancity
Info
Areas of expertise
, generative AI, large language models (LLMs), machine learning and deep learning, language and sentiment analysis...
Dr. Antoun Yaacoub
Head of the MSc in Generative Artificial Intelligence