Independence 2-10 / Essay
Independence 2-10 № 10 · 2026

Preparation is the main body,
AI the last move.

OCR, classification, codifying tacit knowledge — move scattered, unwritten knowledge into a written, structured state. A no-regret investment you recover even without AI.

By here, the parts are in place. Foundation, gate, documents, code, mail, meetings, web, API — the tools stand. But the information itself that flows over them is still scattered. Files sunk to the bottom of a shared folder, paper and scanned PDFs, and the heaviest of all — tacit knowledge that lives only in someone's head.

Before you put AI on top, there is work to do: build information worth putting it on.

Preparation is the main body, AI the last move

Don't get the order wrong. RAG, and your own AI, stand only on prepared information. Put the cleverest model you like on scattered, unwritten information, and what comes out is garbage (garbage in, garbage out).

So this chapter comes before the AI. The work is three things — read the paper (OCR), align the scatter (classification and structuring), write out what's in people's heads (codifying tacit knowledge).

And this preparation has two properties.

Prepared information beats a cleverer model. Preparation is the main body. AI is the last move.

Read the paper — OCR

The first barrier is information a machine can't read. Paper, scans, image PDFs, handwriting.

# example: give a scanned PDF a text layer (OSS OCR)
ocrmypdf --language eng input.pdf output.pdf   # searchable PDF + text

Aim the output at Markdown and plain text. Don't lock it into a proprietary format — so that later anyone, and any AI, can read it (the standard-format principle of 2-04).

Align the scatter — classification and structuring

Next, align the scattered files.

Here AI is a powerful assistant. "Classify these 200 files by type and add a summary" — classification and summarization both run on the local model (2-11). But the axis of classification is decided by people. What counts as "the same type" for the business is something only those who know the business can tell.

Write out what's in people's heads — codifying tacit knowledge

The heaviest, and most valuable, is unwritten knowledge. The vague parts of a spec, the exception handling, the reasons things are the way they are — all in the head of a veteran in charge. When this disappears, the system becomes "it runs, but no one understands it" (the human dependency of 3-04).

The method is the same one used for core logic in 2-09 — interview the people on the ground, have AI draft, and have the ground confirm.

The moment tacit knowledge is written down, it becomes a transferable asset. Independent of whether you ever put AI on it, the company gets stronger right here.

And then, mount the AI

Only once the prepared information is in place comes the next chapter. Embed the written, structured documents into 2-02's pgvector and mount RAG on them (2-11).

Skip the preparation and build RAG, and the sources are vague and the answers unreliable. With the preparation done, an AI that answers from your own real data, with citations, stands up cleanly.

RAG quality is decided not by the model's cleverness but by how well the information you mounted is prepared.

Summary

Before the AI, prepare the information.

Preparation pays off even without AI on top — personnel lock-in dissolves, handover gets easier. Preparation is the main body. Prepared information beats a cleverer model.

In the next chapter, on top of this prepared information, we set up our own AI.


Related articles