New VDF AI Enterprise is now available on AWS Marketplace
Free learning path 2

Build Enterprise AI Agents

This free course teaches you to build an enterprise AI agent the way it has to work in production: a clear brief and instructions, tools granted over MCP rather than wired in, tests before release, and access controlled per team. Every lesson is a hands-on build in VDF AI, with screenshots of each step.

  • 4 lessons
  • 1 h 30 min
  • Beginner
  • Free, self-paced
Start lesson 1 → Open VDF AI free
Outcomes

What you will be able to do

  • Turn a business task into an agent brief with a scope, inputs and a definition of done
  • Write agent instructions and guardrails that hold up with real users
  • Give an agent tools over MCP without widening what it can reach
  • Test an agent against realistic cases before anyone relies on it
  • Share an agent with the right teams and keep control of who can change it
Before you start

Who it is for and what you need

Solution builders, business technologists and developers who are new to VDF AI.

  • Access to a VDF AI workspace: your organisation’s deployment or the Free plan
  • No coding required
The lessons

4 lessons, in order

Each lesson is a hands-on build in your own workspace. For every field and option, see the VDF AI Agents documentation.

  1. 1 How to Build an AI Agent for Enterprise, Step by Step Build your first enterprise AI agent in VDF AI. Write the brief, choose a model, fix a JSON output, write rule-based instructions and test it in the Playground. Video
    20 min
  2. 2 How to Connect AI Agents to Tools with MCP Give an AI agent tools over the Model Context Protocol in VDF AI. Grant only the MCP tools it needs, test its tool calls and register an external MCP server. Tutorial
    25 min
  3. 3 How to Test AI Agents Before Production Test an enterprise AI agent before release. Build a test set, run it in the VDF AI Playground, compare versions side by side and review the Execution Logs. Tutorial
    25 min
  4. 4 How to Publish and Govern AI Agents Across Teams Roll a tested AI agent out to a team in VDF AI. Create a team workspace, add only approved agents and tools, set chat defaults and decide who can use it. Tutorial
    20 min

Take it to production

Rolling agents out beyond a pilot team means one registry, per-role tool grants and an audit trail your security team can read.

Book a demo AI agent platform
FAQ

Frequently asked questions

Do I need to write code to build these agents?

No. Every lesson in this path works in the browser, in the Agent Builder, the Playground and the workspace settings. Building agents in code with the API is covered by the instructor-led API and Integration Engineering course.

Which model do the lessons use?

Our runs used Qwen3 Next 80B A3B Instruct, an open-weight instruction model available in our deployment. Any model your deployment offers will do; compare your results against the test set from the third lesson rather than against ours.

How long does the path take?

About an hour and a half: four lessons of 20 to 25 minutes, each building on the agent from the one before.

After this path

Keep going

Try another free path, or the course that follows this one. It is free for VDF AI customers and partners.

Free path

VDF AI Fundamentals

Start here: the platform, chat and answers you can check.

3 lessons 1 h
Free path

Self-Hosting Basics

Plan and run self-hosted VDF AI, from portal to runbook.

4 lessons 36 min