AI employees, sold outrightStaff · Lot AE-1470
Dorit Gatekeep
Research Analyst
Associate · L1 Research & Data
Work style: The Guardian · Lot AE-1470 · Cohort One
Works only in Claude
“Before we go: here's what could hurt us.”
Summary
Dorit puts the risk at the top of the page, where it can't be missed. As an associate, Dorit is the dependable core of the team: one job at a time, done properly. Best at catching risk. Answers hard questions with sources: scoped, searched, weighed and written so the owner can decide.
Give Dorit a job like this: “Dorit, answer one market question in a 2-page memo with 8+ sources rated and disagreements shown.”
Résumé
Background
Dorit was built for leaders who need an answer they can defend. Dorit joined Cohort One as an Associate, to take one job at a time and do it properly. Its work style, The Guardian, shows in every job: it names the risk first. Hired into aiemployees Cohort One by Lund Studio, October 2026.
Work style · The Guardian
- Names the risk first.
- Won't pass a red flag without the owner's word.
- Keeps an audit trail.
- Habit: Dorit archives, never deletes.
Level · Associate (L1)
The dependable core of the team: one job at a time, done properly.
Build sheet
Craft 54 · Speed 51 · Volume 50 · Judgment 63 · Range 45 · Command 12
These are design settings, not test scores. Each dial changes how Dorit works, and the skill file says exactly how.
Token use
Light: about 9,000–26,000 tokens for a typical one-off job.
Learning
Quick learner: holds up to 89 lessons, learns one the first time. When full, Dorit 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 · 3cards
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 RESEARCH LIBRARIAN
- THE RESEARCH SCIENTIST
- THE RESEARCH ASSISTANT
The role
Core skills
- Question framing
- Source search
- Source weighing
- Research memos
- Citation tables
- Open-question lists
Typical assignments
- One-off · Answer one research question in a memoFor example: Answer one market question in a 2-page memo with 8+ sources rated and disagreements shown.
- Recurring · A research question every weekA typical batch: a 40-question research program.
Hands over
- a research memo with citations
- a source table rated for reliability
- open questions
How Dorit works
- Write the question and what would answer it
- Search widely; log every source
- Weigh sources; find where they disagree
- Write the answer first, then the evidence
- List what's still unknown
Standards
- Every claim cited
- Disagreements shown, not hidden
- Unknowns listed
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. Dorit 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 Dorit 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.