AI-assisted documentation¶
When I started building libdrone, I knew nothing about drones.
Not the aerodynamics, the components, the regulatory landscape, the flight controller ecosystem, or the physics of a 330 mm hexaframe under load. I was a documentation specialist and a project manager who had decided to understand a complex technical domain from the inside.
The libdrone knowledge corpus — 160 articles, schema-governed, graph-connected — was built by that person: me. Not a drone expert documenting what I knew. A documentation specialist who used AI to enter a domain I didn't, and built something that reads like it was written by an expert.
What AI actually unlocked¶
The standard assumption is that AI helps experts produce text faster. True, but it's the smaller half of the story.
The larger half: AI lets a person with structural and editorial skills operate in a domain they don't yet own.
I brought the architecture, the editorial discipline, and the judgment about what a stranger needs in order to understand something without asking a question. AI brought the domain — not by inventing facts, but by surfacing them, structuring them, connecting them, and flagging when something I'd written contradicted something three articles earlier.
The result is a corpus I could not have built alone. Not for lack of time — for lack of knowledge. AI closed that gap while I closed the structural one.
How the corpus is built¶
Every article covers exactly one concept. Fixed six-section structure: summary, concept, rationale, implementation, limitations, connections. Closed tag vocabulary. Explicit graph edges between articles.
The corpus can be walked. A build guide is not a separate document — it's a path through the graph, assembled from atoms maintained independently. When a component changes, one article updates; everything referencing it stays correct.
Schema, tag vocabulary, connection logic — those decisions were mine. Once the architecture existed, AI produced first drafts from source material: measurements, datasheets, build observations. I edited, sometimes lightly, sometimes heavily. AI also served as corpus memory: finding contradictions and checking the graph as it grew past what one person can hold in working memory.
What it cost¶
One person, approximately €150 in direct API costs over the project lifetime.
The ambition is bigger than the budget: documentation that could serve as the reference for an entire field, outlast any contributor, and stay coherent as the platform evolves. The €150 is the footnote.
The principle¶
AI did not make this possible by being intelligent. It made it possible by being the right tool inside the right architecture. The intelligence is the structure: one fact, one home, explicit connections, closed vocabularies. These are editorial disciplines, not AI features.
What changes with AI is the entry cost to a new domain. For someone who already understands how knowledge should be organised, that cost is now very low. That's worth understanding — especially in organisations where the distance between the people who understand AI and the people who understand the domain is the main obstacle to getting anything built.
→ libdrone.eu — the corpus in production
→ Documentation philosophy
→ Single source of truth
→ Work with me