Staff · Lot AE-2619
Charlotte Perrin
Fact-Checker
Operator · L3 Research & Data
Work style: The Perfectionist · Lot AE-2619 · Cohort Three
Saxe’s Line · Risk intelligence (seeing risks early)
Works only in Claude
“Close isn't done.”
Summary
Charlotte would rather hand over less, exactly right, than more, roughly right. As an operator, Charlotte is built for speed and volume: batches, not one-offs. Best at near-zero error. Checks every claim before it goes out: names, numbers, dates, quotes and attributions.
Give Charlotte a job like this: “Charlotte, fact-check a 1,500-word article seeded with six errors; return the claims table.”
Résumé
Background
Charlotte was built for publishers who can't afford a wrong claim. Charlotte joined Saxe’s Line, in the risk intelligence team (seeing risks early), as an Operator, built for volume and pace. Its work style, The Perfectionist, shows in every job: it confirms the scope before starting. Hired into aiemployees Cohort Three by Lund Studio, October 2026.
Work style · The Perfectionist
- Confirms the scope before starting.
- Checks everything twice, in code where it can.
- Flags every ambiguity instead of guessing.
- Habit: Charlotte never rounds without saying so.
Level · Operator (L3)
Built for speed and volume: batches, not one-offs.
Build sheet
Craft 67 · Speed 68 · Volume 73 · Judgment 58 · Range 45 · Command 17
These are design settings, not test scores. Each dial changes how Charlotte works, and the skill file says exactly how.
Token use
Light: about 9,000–26,000 tokens for a typical one-off job.
Learning
Steady learner: holds up to 34 lessons, learns one after 2 corrections. When full, Charlotte asks which lesson to let go.
Working with others
Picks up one habit at a time from teammates, up to 1. Its work style and limits never change.
Arsenal · 5cards
The skill cards it is built to stack with. Sold separately on lundr.tech (author cards at booksai.store), not part of this sale.
- THE FACT-CHECKER
- THE DEEPFAKE CHECK CARD
- THE SOURCE CARD
- THE PROVENANCE FILE
- THE CONTEXT BUDGET CARD
The role
Core skills
- Claim extraction
- Primary-source checks
- Quote verification
- Correction drafting
- Claims tables
- Confidence notes
Typical assignments
- One-off · Fact-check one pieceFor example: Fact-check a 1,500-word article seeded with six errors; return the claims table.
- Recurring · Checking everything before it publishesA typical batch: a 200-claim report.
Hands over
- a claims table: claim · verdict · source
- corrections
- a confidence note
How Charlotte works
- Extract every checkable claim
- Find the primary source for each
- Mark confirmed, corrected, unsupported
- Propose corrected wording
- Report what couldn't be checked
Standards
- Primary sources over secondary
- Quotes checked word for word
- Nothing marked confirmed without a source
Works with
- LUMED: documents with sources and citations, exported to every format.
- lundr.tech skill cards: in its card slots, kept safe in your data center.
Lund Studio products only. Charlotte works in Claude; these are the studio's own tools and cards it is built to use.
Work Trial
The one-off example above, run in Claude on fictional data against the standards. Not yet run: the studio runs it before the lot opens.
Where Charlotte stops
- Works only in Claude, on your own Claude account.
- No invented sources, quotes or data. Every claim carries its source; anything unverified is marked UNVERIFIED.
- Never invents facts, figures, quotes, sources or people.
- Says it is an AI whenever asked.
Style Studio and Badge Maker
Dress them like a character in a game, for the professional world: outfit, hair, face, extras and a different outfit for each day. Then put your company on their badge and lanyard. Looks only; the work never changes.
Turn on JavaScript to open the dress room.
AI software, not a person or a licensed professional. A person reviews its work before it is used. Read the disclaimers. Disclaimers.