Knowledge & data
Project knowledge base
After every event it's the same story: your head is full of lessons – which caterer delivered, why the schedule fell apart, which supplier you'll never book again – and three weeks later most of it is gone. On the next project you start from scratch.
You'll get …
- 1
Project knowledge that stays
Suppliers, venues and the lessons from every debrief are on record – even when someone goes on parental leave or quits.
- 2
Look it up, don't interrupt
Before a quote goes out, the team finds suppliers and past experience, with the source.
- 3
Every event makes the next one smarter
The AI writes up debriefs and lessons learned, and every change needs sign-off. That way the lessons feed into the next quote.
01Intro
The project knowledge base keeps what agencies otherwise lose to post-teardown exhaustion: contacts and supplier knowledge with ratings, venue profiles, decisions and risks for each project, the lessons from every debrief. It's a structured system the team searches instead of asking around – and where AI lends a hand.
Worth knowing: I won't promise a "second brain in one go" – you start with one area, such as the supplier directory, otherwise it falls apart on upkeep. Client data and confidential material stays out or gets its own concept. The AI never writes anything unchecked – every debrief and every new contact needs sign-off. And the system only stays alive if the team spends two minutes on it after every event.
02How it works
- 01
Take stock: where does your project knowledge live?
In heads, old email threads, scattered Google Docs, the contact list on the boss's phone. Also: what knowledge walks out of the door when someone leaves, and which mistakes keep happening from one event to the next?
- 02
Build the structure – small and documented
A clear filing system: contacts and suppliers, venues, events with debriefs, lessons learned. With simple rules – and a clear line on which client data stays out.
- 03
Fill one area first
Usually the supplier and contractor directory: who can do what, at what scale, how reliably – including the lessons that cost money. Existing material moves in curated, not copied.
- 04
Connect the AI: read first, write later
At first the AI only answers questions from the knowledge base – with the source. Once that works reliably, writing with sign-off follows: debriefs, contact entries, suggested lessons. Permissions and limits are set out in a written work instruction.
- 05
Add routines – one at a time
A morning overview of critical event deadlines, a debrief template after every project, follow-ups on open quotes: 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, the team knowledge base – for agencies, suppliers and lessons learned are the right place to begin.
Starter: a knowledge base you can ask
One clearly defined area – suppliers and venues with ratings – is organised so you can ask it questions. The team looks things up instead of ringing the colleague on parental leave.
Next step: the AI joins in
Debriefs, summaries, lessons learned – the AI writes in the system alongside you, and every change needs sign-off.
Full build: routines run themselves
Deadline overview, automated debriefs, follow-ups – defined routines run on their own within clear limits. The knowledge base becomes the agency's project memory. 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 project knowledge base of the fictional event agency “Kollektiv Nord” – on the left the order in which contacts, suppliers and event learnings 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 the agency: 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 clear line on client data: confidential material (contracts, personal data) stays out or gets its own data-protection concept; the knowledge base holds suppliers, venues and your own lessons learned.
- 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 debrief after every event is what keeps the knowledge base from going stale.
- Typical content: supplier and contractor directory, venue profiles, event debriefs, risks and lessons learned, contact history.
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.