 ← Lab/LAB · 02PIPELINE 

Wiki–LLM research pipeline

An audit is only as trustworthy as the process behind it. This is the machine: public sources in on the left, evidence-cited findings out on the right, every claim traceable to where it came from.

SOURCES → EVIDENCE → FINDINGS

IN: SiteDocsGitHubDiscordX / postsSearchScreenshots

›

Collect

Every public surface, captured and dated.

→ dated captures

›

Normalize

Screenshots and pages become clean, searchable markdown.

→ the corpus

›

Extract

Pull the claims, contradictions, and open questions out of the noise.

→ claim list

›

Evidence

Tie each claim to its source and a verdict — verified, contested, unbacked.

→ evidence matrix

›

Synthesize

The patterns across claims become findings, ranked by risk.

→ findings, ranked

Translate

Findings become the maps, the report, the fix list.

→ the deliverables

OUT: Evidence-cited findings ledger Trust & confusion maps

HOW TO READ IT

Left to right, raw public material becomes structured evidence. Each stage produces one artifact the next stage builds on. Nothing reaches a finding without a source attached.

WHY IT MATTERS

The desk's whole promise is "we cite the public record." A promise like that has to be a system, not a habit. This is where the citation comes from — every claim in an audit traces back through this pipeline to a dated capture.

See the method →

SOURCE / METHOD

The real Obsidian + LLM vault workflowSources normalized to markdownClaims held in an evidence matrixStatic schematic of the live system

Wiki–LLM research pipeline

Collect

Normalize

Extract

Evidence

Synthesize

Translate

More from the Lab

Public-signal audit, as a poster

Fork confusion map

The pipeline, on a real launch