software-architecture.aiYour brand can't stay inside your head.
You know why one supplier was kept and another rejected. As long as that lives only in your head, the brand is a single point of failure. I build the system that makes your decisions reachable for team and tools. Without freezing them.
Values decisions
Which partnership gets declined · which supplier kept · which tone in crises
Context knowledge
Why this wool producer in Portugal · why natural rubber not synthetic · why this packaging
Heuristics
How complaints get sorted · how trend requests get judged · how influencers get filtered
Brand memory
What's already been tried · what was community-loved · what didn't work
Three places, one system.
Founder knowledge
Knowledge out of your head into the system
Four recurring patterns.
What happens as long as the brand knowledge doesn't leave your head.
You get DM'd privately, even when you're not working.
On values decisions someone else can't or won't make. Influencer requests, unusual partnerships, edge cases. The reply takes you three seconds. The question keeps showing up every weekend.
Onboarding is a one-person show.
New people ask a lot, and rightly so. Why this supplier, why this material, why this packaging. You explain it every time yourself. Not scalable, and the effect only shows once you're worn down.
Decisions in the team drift.
When someone in your absence agrees to a partnership you would never have agreed to, that's rarely bad faith. It's missing context. What you know implicitly, the team doesn't.
Service replies lose context.
A complaint gets answered politely and correctly. What's missing: that this person has ordered before, that something similar happened last time. Information like that often only sits in your head, not in the ticket.
Two options as long as the knowledge stays unsorted: decide everything yourself and never fully step away, or delegate and correct later. Both cost. One time, the other trust.
What it is. And what it explicitly isn't.
A lot gets misunderstood here. Founder knowledge isn't what you know. It's what you do when you decide, without noticing.
- Not a Notion wiki nobody maintains, that becomes a graveyard of stale pages after three months
- Not a Custom GPT that gets the brand manual as context and pretends to be you
- Not an onboarding PDF the new hire reads on day one and forgets by day three
- No SOPs. A brand doesn't have Standard Operating Procedures, it has values and heuristics
A documented system of four knowledge layers.
Values decisions
What you held, what you turned down. And why.
Context background
The stories behind the decisions. What shaped the brand.
Heuristics
The rules of thumb you no longer apply consciously.
Brand memory
Anchors, anecdotes, brand moments. The invisible continuity.
Founder knowledge is less what you know.
More what you do when deciding, without thinking about it.
Four layers. So not all knowledge gets treated the same.
Not every kind of knowledge belongs in the same drawer. Values decisions need a different format from supplier context, and heuristics work differently from brand memory. These four layers have proven a robust split.
Values decisions
Which partnership gets declined · which supplier kept · which tone in crises
Context knowledge
Why this wool producer in Portugal · why natural rubber not synthetic · why this packaging
Heuristics
How complaints get sorted · how trend requests get judged · how influencers get filtered
Brand memory
What's already been tried · what was community-loved · what didn't work
- 01
Values decisions
The decisions where the brand defines itself. Which influencer yes, which no. Which supplier stays, even when they get more expensive. How you communicate in a crisis. The most important layer and the hardest to document, because the decisions are often gut-driven. The job: translate the gut into criteria.
- 02
Context knowledge
The background to your material, supplier and product decisions. Who sits in Portugal and why. Why one material and not the other. Which packaging serves which trade-off. From this layer the team can answer questions when customers ask, without you in the loop.
- 03
Heuristics
Your micro-decision rules. When someone writes the product feels different, what are the three questions you ask yourself. When a trend turns up, what are the two filters. When an influencer asks, what are the five points you check inside two minutes. Heuristics run on autopilot for you. Documented, they become useful for the team.
- 04
Brand memory
The institutional memory of the brand. Which launch didn't go as planned and why. Which campaign was a community favourite and what the ingredients were. Which step got reversed and what the lesson behind it was. This layer keeps the team from repeating mistakes in two years that you've long solved.
How to capture founder knowledge without cloning you.
The most delicate question of the whole project. My intent isn't to replicate you. My intent is to mirror the system as you would have decided yesterday, so the team and the tools can build on it today. What you decide tomorrow stays your call.
AI-supported knowledge interviews
Three to five sessions of sixty minutes where you talk and I take notes and probe with the help of a language model. You speak, I structure, the model helps surface gaps. Concretely: I dig into ten of your last values decisions, have you describe how you respond to a particular kind of complaint, and walk through your supplier list. From these sessions comes the raw material of the four layers.
Slack and email archive analysis
With your approval, I look in a structured way at the last twelve months of Slack and email where you commented on values decisions. A goldmine, because your gut sits there in real sentences, often more precise than you would say it in an interview. GDPR-compliant, processed locally, with a clear deletion deadline after project end.
Decision diary over three weeks
For three weeks you document every values decision in two sentences. What was the question, what did you decide, why. Effort: honestly about fifteen minutes a day. The only method that catches the gut in real time, before you've rationalised it.
Negative library of misjudgements
Equally important. Which three decisions would you make differently today, and why. These negatives sharpen the system more than ten positive examples. They tell the founder brain what doesn't belong to the brand, which makes the filter logic realistic.
The system mirrors what you would have decided yesterday. What you decide tomorrow stays your call.
How it runs
Six steps. Clear order. You see every iteration.
- 01Step 1
Knowledge audit
Map the pain density. What are the most frequent questions landing in your Slack today. Which decisions got escalated to you in the last three months that shouldn't have. Where did you delegate and correct after the fact. Outcome: a knowledge heatmap of your current reality.
- 02Step 2
Knowledge interviews
Three to five sessions of sixty minutes where the raw material of the four layers emerges. In parallel the decision diary runs over three weeks, if you commit to it.
- 03Step 3
Structuring into four layers
Values decisions, context knowledge, heuristics and brand memory get filled, with concrete examples from your material. This phase is intense, because the translation between gut and documentation happens here.
- 04Step 4
Engine build
Notion structure, RAG system, Slack integration. Optional: voice bridge to Place 1, service bridge to Place 2. You see iterations, you test, you give feedback.
- 05Step 5
Pilot with one team member
One person on your team uses the founder brain in their daily work, three to four weeks. They log: which question got answered well, which badly, where they still asked you. This phase fine-tunes the system before the whole team gets access.
- 06Step 6
Roll-out and update loop
The team gets access. Quarterly update sessions are built in: new values decisions, new heuristics, new brand memory. Plus a clear escalation logic: when do you decide yourself, when may the system answer.
Knowledge inventory
By the end you have a map of your implicit knowledge. You see what only lives in your head, what's already partly documented, and which layer needs to be lifted first.
What you get
- 2 × 90 min founder interviews (remote, structured across four layers)
- Layer map: values, context, heuristics, memories, weighted by risk
- Prioritised list: which layer to document first
- Structured doc set in Notion, Confluence, Obsidian or the documentation tool of your choice, as a starting point for your own upkeep
Format
2 × 90 min interviews, remote only. One week of processing.
Fixed price
€1,490
plus VAT, one-time.
Frequent questions
Fair question, because RAG is being worn out as a buzzword. The difference is in the substance and in the architecture. A Custom GPT with the brand manual as context sounds hollow after three days. It doesn't know anything real. What I build is more than classic vector retrieval: an information network of values decisions, context knowledge, heuristics and brand memory. Vector search is just one layer. On top of it come knowledge graphs, rule logic and context-sensitive routing. So the system actually knows why your wool producer sits in Portugal. Not just that they're there.
If you recognise the pattern.
Before we build knowledge layers, we look at how deep they actually need to go. 60-minute knowledge diagnosis for €99, no sales pitch. I take samples from your current knowledge sources, look at your setup and tell you whether Place 3 is up now or can still wait, whether to build it before or after the other two. If you want to go deeper afterwards, a full knowledge audit typically takes two to three weeks and costs €1,490.