Knowledge & data
AI knowledge system for your knowledge
Your knowledge is your business – and it's scattered all over the place: the method in your head, the exercises in five different folders, the good wording in old emails, the session notes on paper. Every time you put together a new offer, you collect what you already have all over again.
You'll get …
- 1
Your knowledge in one place
Method, exercises, programmes and content ideas sit together in one organised place instead of five folders.
- 2
Your exercises in seconds
You ask your own knowledge base and get your exercises and notes with the source – on the go, too.
- 3
A system that grows with you
Session notes turn into drafts for your method and content, and every change needs sign-off. Anything personal about clients stays out.
01Intro
For coaches and consultants, knowledge is the asset: method, exercises, programmes, content ideas and lessons from sessions live in one place, organised so that AI can search them, summarise, take notes and run routines. I work this way myself – much of my day-to-day business now runs through a system like this, with AI as a colleague inside it.
Worth knowing: I won't promise a "second brain in one go" – you start with one area, such as your exercise library, otherwise it falls apart on upkeep. And the most important point in coaching: anything personal about clients stays out or gets its own strict data-protection concept – the system holds your method, not your clients' stories. The AI never writes anything unchecked.
02How it works
- 01
Take stock: where does your knowledge live?
In your head, folders, course handouts, wording in old emails, session notes. Also: what do you keep piecing together again, and what would be lost if your laptop died tomorrow?
- 02
Build the structure – small and documented
A clear filing system: method, exercises, programmes, content, lessons learned. With simple rules – and a firm line that anything personal about clients doesn't belong in it.
- 03
Fill one area first
Usually the exercise and method library: what do you have, when do you use it, how has it worked for you? Existing material moves in curated, not copied.
- 04
Connect the AI: read first, write later
At first the AI only answers questions from your knowledge base – with the source. Once that works reliably, writing with sign-off follows: filing session notes, content drafts, programme modules. Permissions and limits are documented.
- 05
Add routines – one at a time
Session prep in the morning, a content pipeline fed by session lessons, follow-ups on open inquiries: the AI takes on defined tasks within clear limits – each one only once the previous one is running smoothly.
03Stages
Every project starts with Tier 1 – for solo coaches, the method library is the right place to begin.
Starter: knowledge you can ask
One area – your exercises and method – is organised so you can ask it questions. In seconds you find what you'd otherwise hunt for across five folders.
Next step: the AI joins in
Filing session notes, content drafts, programme modules – the AI writes in the system alongside you, every change needs sign-off, and anything personal about clients stays out.
Full build: routines run themselves
Session prep, content pipeline, follow-ups – defined routines run on their own within clear limits. The knowledge system becomes your back office. To get there, it needs deep access to your data and processes. That's why Tier 3 only comes after a baseline assessment, once Tier 2 has proved itself for a while, and runs as a project I support throughout.
04Demo
The knowledge system of the fictional coach “Anna Baur” – on the left the order in which method, programmes and content live, on the right three everyday moments with it. Click through and watch where it lights up in the tree.
The architecture behind it has two layers: at the bottom the vault – structured folders and notes that belong to the business. Above it the AI layer with documented rules: it reads only at first, then writes with approval, and sensitive areas stay locked. Calendar and tools dock on, routines run within clear limits.
The proof of this model: this website came about this way – I work in such a system myself every day, with AI as an employee inside it.
05Technical implementation
- The knowledge layer belongs to you: a Markdown vault (e.g. Obsidian), Notion or a similar system – your content, no vendor lock-in.
- The AI layer is an assistant with access to the vault (e.g. Claude Code as the agentic layer), working to documented rules: which areas, which permissions, which routines.
- A hard line on client data: anything personal, including session content tied to real people, stays out or gets a strict data-protection concept.
- Permissions in stages: read access first, write access only in defined areas and with sign-off.
- Upkeep routines are set up from the start – the two-minute note after each session is what keeps the system from going stale.
- Typical content: method and frameworks, exercise library, programme outlines, content ideas, anonymised lessons learned.
for context · This shows how something like this usually gets built – not how it has to be built for you. What actually fits is worked out in the project: around your existing setup, your team, and what stays easy to maintain.