the cleanest graph engineering setup I've seen
12,571 claims in, zero rows ever updated, and the whole index rebuilds from the log in 8 seconds
three Claude agents share one store:
one pulls claims out of raw sources, one proposes how they connect, one checks each claim against what's already there
every claim gets appended with a timestamp and a source, and nothing is ever overwritten
• the schema
> nodes.yml - entity, claim, source, artifact, run
> edges.yml - supersedes
> an ids file - one id per entity, aliases listed
• the store
> log/ - one jsonl per day, sealed when the day ends
> blobs/ - sha256 filenames, so duplicates cost nothing
> index.duckdb - derived, safe to delete any time
• the writers (.claude/agents/)
> extractor - a source in, claims out
> linker - proposes merges, never merges
> checker - supports or contradicts, always with a reason
> the write script - the only way in: validates, appends, exits
• the operations
> queries/ - every question saved as sql
> merges.pending.jsonl - a human approves each one
> make rebuild - the full index back from the log
when something's wrong, you append the correction and let the log outvote the mistake
the full road from zero to graph engineer is below 👇
we've been using Claude f*cking wrong on agent actions too
your agent reads a YouTube comment, drafts a reply, posts it. no gate in front of the post. one legal threat it waves off as friendly, one hallucinated promise, one spam comment it feeds back as a quote, and 100k subs see the stupid reply before you do.
Jev flips that too.
it's a mode of Jev that cannot write a single word. you give it the event and 3 questions in parallel, it gives back one of three typed answers:
-> a choice from your options -> a score on your scale -> a yes/no
each with a confidence, so your code knows whether to run it or send it to a human.
that's the whole mode.
-> 354 ms per gated decision -> $0.018 per million input tokens -> output is free
-> 10,000 gated decisions for around $0.42
that's not because Jev reads your comments better than Claude.
it's because nobody asked it to write the next thing.
let Claude draft the reply. let Jev decide if it ships. let code gate the action behind the confidence.
the catch: the gate is only as good as the question. "is this reply safe?" is testable, "is this reply good?" is not. keep the heads narrow and the thresholds measurable.
how to wire the 3-head gate in front of every agent action + the exact Choice/Score/Noul schema in the article below
To the reader who inherited a marble Washington—and wants the man of fire, calculation, and self-command underneath — this is for you.**
Washington: A Life by Ron Chernow**
Winner of the 2011 Pulitzer Prize for Biography
From the author of *Alexander Hamilton*, a one-volume life of George Washington.
Chernow takes Washington from a troubled boyhood through the French and Indian War, the making of Mount Vernon, the Continental Army, the Constitutional Convention, and the first presidency. The aim is a portrait as real and charismatic as the one his contemporaries saw—not the lifeless waxwork of later reverence.
A laconic man of granite self-control, Washington often draws more respect than affection. Chernow works against that stereotype: a celebrated horseman and dancer, a man of fierce opinions and a guarded inner life, a complicated husband and slaveholder, and a canny political genius who gathered Hamilton, Madison, Adams, and Jefferson and shaped the new federal government.
Based on massive archival research. A long book with a crisp pace.
Buy links
- Amazon (paperback): https://t.co/9iffHVZXs5
- Amazon (hardcover): https://t.co/n1rTLt9Wio
- Amazon (Kindle ebook): https://t.co/POwAOUSAEf
- Author site: https://t.co/FitAuPagGN
About the author
Ron Chernow is the author of *The House of Morgan* (National Book Award), *Alexander Hamilton* (George Washington Book Prize; the book that inspired the musical), *Washington: A Life* (Pulitzer Prize), *Grant*, and *Mark Twain*. He received the National Humanities Medal in 2015.