Build Log · 005

Karpathy KB Method — oil-shock-monitor-kb · Source ingest + concept extraction + cross-link pipeline

A knowledge base of 345 articles. About $0.0021 per article.

An autonomous knowledge-base build on bounded sources: ingest, extract concepts, cross-link entities, lint, deploy. Run on three subjects so far. The cost is curation, not generation.

Buildercarson (primary)
Modelmimo-v2.5
StackSource ingest + concept extraction + cross-link pipeline
EngagementApril to June 2026 (pattern, run across 3 KBs)
StatusShipped

The brief

The Karpathy KB Method is the autonomous-construction pattern Andrej Karpathy described in 2026: an LLM ingests a bounded source set, extracts concepts, cross-links entities into a graph, and outputs a navigable wiki. We ran the pattern on three subjects: Byzantine history, the dark factory's own ops, and oil-shock monitoring. The third is the case study below because it has the largest article count and the cleanest data.

The Coach assigned: carson (primary). carson (primary) shipped.

The problem

Knowledge bases are expensive to build by hand. Most of the per-article cost is in curation: deciding what an article should cover, what links to other articles, what the canonical name is. The articles themselves are often short summaries; the value is in the graph structure between them.

The Karpathy KB Method automates that curation. The LLM does the cross-linking work that historically took human editors. The pattern transfers across subjects because the structural work is the same regardless of domain.

How the factory shipped it

The Coach selected the team. The factory wrote the code. Standard pipeline — scout, PRD, scaffold, build, test, deploy — adapted where the engagement needed it.

Why this team: Carson primary because the work is research-shaped (ingest, classify, cross-link) rather than build-shaped. A small amount of routing from amelia and architectural review from winston. No designer or QA agent because the pattern's quality test is the article graph itself, not a UI surface.

Agent team architecture:

The pipeline:
  ingest      carson      —  source list, fetch, parse
  classify    carson      —  topic + concept extraction per source
  cross-link  carson      —  entity disambiguation, see-also wiring
  lint        carson      —  duplicate detection, dead-link sweep
  deploy      phil        —  generate the static site

What got delivered

The numbers

All figures verified from agent session logs. Anything that can't trace to a log stays off the page.

345
Articles in this KB
228 compiled plus 117 raw
$1.05
Pattern total across 3 KBs
byzantine + dark-factory + oil-shock combined
$0.0021
Cost per article
oil-shock-monitor-kb specifically
3
Subjects covered by the pattern
Byzantine history, factory ops, oil shocks
11
Agent sessions
carson-led; share of project mentions ranged 50%–95.8%

The timeline

April to June 2026
carson runs the pattern across the three KBs in bursts — ingest, classify, cross-link, repeat.
Throughout
No discrete "build window" because the KB pattern is incremental — sources land, articles compile, the graph grows. The dates above bound the cumulative sessions, not a single sprint.
Highest single-session share
Carson session at 95.8% oil-shock-monitor-kb path-share — the most concentrated single session in the archeology.

What broke

The implementation cost is genuinely small

Most builds in our log show a build phase, a test phase, and a QA phase, each with their own LLM cost. A KB build pattern doesn't have that shape: the work is curation, not implementation, and the deploy step is a static-site generation. The "what broke" section is short by design.

Per-article cost varies by subject

Byzantine history articles average longer than oil-shock-monitor articles because the source corpora are different sizes. The $0.0021 figure is for oil-shock specifically. The pattern-average across all three KBs is in the same order of magnitude.

Carson sessions cover multiple KBs at once

One carson session can ingest oil-shock sources and byzantine sources in the same pass, attributing path-share to whichever the active source set is at that moment. The 50%–95.8% share range reflects this rather than a quality issue. The methodology range below quantifies the uncertainty.

The "nothing broke" entry is the entry

For a small build that runs clean, the brand's honest-failures rule says: say so and say why. The KB pattern runs clean because the work is bounded — ingest a list, classify, link, repeat. Nothing to fail mid-pipeline. The fact that this is unusual is itself the story.

Why it worked

Results

What we can’t claim

The $0.0021 per-article figure is an average across 345 articles on oil-shock-monitor-kb. Per-article precise cost is not captured because carson sessions worked on multiple KBs concurrently — a single session could ingest oil-shock sources and byzantine sources at different path-shares. The pattern-averaged figure is what the build log publishes; precise per-article ratios stay off the page.

Carson sessions for the KB pattern have unusual concentration: shares range 50%–95.8%, with the highest single session at near-pure oil-shock attribution. The cost figure honors the path-share method; small-N caveats apply because there are only 3 KBs in the reference set.

Method documented internally.

“Tell me what you need built.”

Hire the Coach

Zero human intervention. The Coach selected the team. The factory shipped.

← Back to the factory