AI KnowledgeBase
You build the knowledge base AI draws on, and test twice whether it works. The difference between test 1 and test 2 is the proof.
What you'll learn
The skills to build a working AI knowledge base for your team, using your own documents.
Write a context document
Describe your knowledge domain so AI knows what it needs to know
Classify sources
Determine which documents you reuse (core) and which you add per task
Make documents AI-ready
Parse PDFs, Excel, and PowerPoint into clean text without information loss
Test with real work tasks
See if your knowledge base delivers usable output, then improve it
Who is it for?
For knowledge workers who've completed the Copilot Fundamentals and want to take the next step. You work in teams of 3-4 from the same domain: product management, analysis, communications, or another knowledge area. As a team lead, project manager, or specialist, you'll build a knowledge base your entire team can use. Ideal when you notice AI output stays too generic because it doesn't know your processes, templates, and guidelines.
Program
A half day or full day of hands-on work in small teams. From cataloguing sources to a working knowledge base.
Demo + Theory
1 hour
Demo + Theory
1 hour
- • Live demo: with vs. without knowledge base
- • Three layers of context and the context document
- • Canvas: scoping your topic and test tasks
Completed canvas + scope defined
Build + Test
2 hours
Build + Test
2 hours
- • Writing context documents and gathering sources
- • Parsing documents: PDFs, tables, screenshots
- • Two test rounds with real work tasks
Working knowledge base + parsed sources
Presentations + Action plan
1 hour
Presentations + Action plan
1 hour
- • Each team demos their knowledge base live
- • Peer feedback and improvements
- • Action plan for the next two weeks
2-week action plan
Why a knowledge base?
AI knows a lot about the world, but nothing about your organization. Your processes, templates, guidelines, and unwritten rules are behind a login or inside someone’s head. Every time you write a prompt, you’re starting from scratch.
A knowledge base solves that. You gather the documents AI needs, make them readable, and write a context document that ties everything together. The result: you hand AI a task and get an answer that sounds like it came from a colleague.
Half day or full day
You choose how many sources you process.
Half day: you map out your sources and fully set up one topic.
Full day: more sources, more documents converted, and the time to really build it out.
What you bring
You bring one topic, five to seven documents, and one real work task to test with. Preparation takes 60 minutes upfront.
How the work session works
The session starts with a live demo: the same task, first without context, then with a knowledge base. The difference is immediately obvious.
Then you work in pairs or trios around a shared topic. On a canvas you map out which sources AI needs and which unwritten knowledge isn’t captured anywhere. You write a context document and learn four techniques to convert PDFs, spreadsheets, and presentations into text a language model can actually work with, without losing information.
The heart of the session is two build-test loops. You build a first version, test it with a real task, spot the gaps, improve, and test again. The difference between test 1 and test 2 is the proof. At the end, each team presents their knowledge base and everyone creates a four-week action plan.
The pace was just right and the explanations were clear. I can work confidently with Copilot now, and the ROI was obvious straight away.
Karel Visser
Alliade
Practical information
- Duration
- Half day or full day
- Format
- On-site
- Group size
- 8-12 participants
- Language
- NL / EN
- Investment
- From €2.650 per group
- Prerequisites
- Copilot Fundamentals or equivalent experience
- Materials
- AI Knowledge Base Canvas + context document + folder structure + parsing guide + action plan
What's included
From €2.650 per group
- Completed AI Knowledge Base Canvas (topic, test tasks, sources, and the knowledge that's written nowhere)
- Context document, second version (the map to everything AI needs to know)
- Folder structure with your sources (organized, so your colleague can open it tomorrow)
- Core documents parsed (PDF or spreadsheet converted into readable text)
- Four-week action plan (three documents, a share moment, a review date)
Coming soon
- Full video course as reference materialComing soon
- AI literacy e-learning for your whole teamComing soon
Your trainers
Our trainers work with organizations like VodafoneZiggo, Rabobank and DPG Media.
Frequently asked questions
How is this different from the Fundamentals course?
What's the difference between the half day and the full day?
Do I need to prepare anything?
Book this course for your team
In a quick 30-minute call, we'll figure out if this course is the right fit for your team.
What comes next
Part of our AI Skills Curriculum. Each course builds on the previous one.
Discover the full curriculum
AI Skills Program