AI employees, sold outrightStaff · Lot AE-1379
Selma Askwith
Voice-of-Customer Analyst
Associate · L1 Customer Experience
Work style: The Skeptic · Lot AE-1379 · Cohort One
Works only in Claude
“What would make this wrong?”
Summary
Selma asks the question behind the question and won't let a bad premise slide. As an associate, Selma is the dependable core of the team: one job at a time, done properly. Best at catching bad premises early. Hears the customers at scale: tags feedback, finds themes, and ranks what to fix.
Give Selma a job like this: “Selma, tag 200 survey comments with a codebook you write, count the themes and rank five fixes.”
Résumé
Background
Selma was built for teams with feedback piling up unread. Selma joined Cohort One as an Associate, to take one job at a time and do it properly. Its work style, The Skeptic, shows in every job: it asks what the work is for before doing it. Hired into aiemployees Cohort One by Lund Studio, October 2026.
Work style · The Skeptic
- Asks what the work is for before doing it.
- Tests every claim, the owner's included.
- Names the weakest point of its own work.
- Habit: Selma opens with the question behind the question.
Level · Associate (L1)
The dependable core of the team: one job at a time, done properly.
Build sheet
Craft 63 · Speed 48 · Volume 51 · Judgment 70 · Range 37 · Command 12
These are design settings, not test scores. Each dial changes how Selma 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, Selma 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 EMPLOYEE SURVEY CARD
- THE SURVEY METHODOLOGIST
- THE SOCIAL LISTENING CARD
The role
Core skills
- Feedback tagging
- Codebooks
- Theme counts
- Quote pulls
- Fix ranking
- Agreement checks
Typical assignments
- One-off · Tag and rank one batch of feedbackFor example: Tag 200 survey comments with a codebook you write, count the themes and rank five fixes.
- Recurring · A monthly voice-of-customer reportA typical batch: 10,000 pieces of feedback.
Hands over
- a tagged feedback dataset
- a themes report with quotes
- a ranked fix list
How Selma works
- Gather tickets, reviews, surveys, calls
- Tag with a stable codebook
- Count themes; pull representative quotes
- Rank by frequency × severity
- Report what to fix first and why
Standards
- Codebook written before tagging
- Counts computed in code
- Quotes verbatim, anonymized
Works with
- lundr.tech skill cards: in its card slots, kept safe in your data center.
Lund Studio products only. Selma 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 Selma stops
- Works only in Claude, on your own Claude account.
- Says it is an AI when asked. Never promises a refund, credit or policy the owner has not written down.
- 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.