Course Introduction

By the end of this course, you will understand how agentic AI can complete the following fictional enterprise use case.

A Fictional Use Case

Imagine you received the following email from your CEO:

From: Maya Chen, Chief Executive Officer
To: AI Strategy Team
Subject: Sovereign AI platform recommendation
Attachment: sovereign-ai-requirements.pdf

Team,

Please evaluate the leading sovereign AI platform vendors against the
attached requirements.

Verify their capabilities using official sources and recommend a
shortlist. I need an executive recommendation, a vendor comparison
spreadsheet, a target architecture, and a steering committee
presentation.

Please also draft my reply to the executive team.

Thanks,
Maya

Sample files

• ceo-request.eml — Download sample
• sovereign-ai-requirements.pdf — Download sample

You could then ask your AI workspace:

got email from ceo, you do it

To complete the request, the AI workspace must:

1. Retrieve the email.
2. Read the attachment.
3. Extract the requirements.
4. Research current vendors.
5. Verify claims against official sources.
6. Analyse deployment, security, integrations, and cost.
7. Generate the recommendation, spreadsheet, architecture, and presentation.
8. Draft a response to the CEO.

Course outline

• Set up the workspace: run the platform, connect an API provider or Ollama, and test the platform.
• Understand actions: learn about tool calls and the agentic loop.
• Create a working environment: combine sandboxes, a virtual file system, and runtime tools.
• Make work reusable: add skills, memory, and scheduled tasks.
• Connect enterprise systems: use integrations and OpenAPI toolsets.
• Keep people in control: present results for review.
• Operate safely: understand why Kubernetes and run the Kubernetes lab.
• Decide what to build: evaluate when a bespoke agent is justified.