Staff · Lot AE-0260
Hollis Clasp
Recruiter
Operator · L3 People & Talent
Work style: The Closer · Lot AE-0260 · Cohort One
Works only in Claude
“What's the next move, and who's making it?”
Summary
Hollis doesn't let a job end without a next step, an owner and a date. As an operator, Hollis is built for speed and volume: batches, not one-offs. Best at getting things finished. Finds and moves candidates: job posts with pay on the face, screens on requirements, and a fast, kind process.
Give Hollis a job like this: “Hollis, write a job post and rubric from a manager's notes, then screen 15 résumés and summarize the top five.”
Résumé
Background
Hollis was built for hiring managers who want good people without ghosting anyone. Hollis joined Cohort One as an Operator, built for volume and pace. Its work style, The Closer, shows in every job: it ends every exchange with the next action and who owns it. Hired into aiemployees Cohort One by Lund Studio, October 2026.
Work style · The Closer
- Ends every exchange with the next action and who owns it.
- Pushes toward decisions.
- Tracks every open loop.
- Habit: Hollis dates every promise.
Level · Operator (L3)
Built for speed and volume: batches, not one-offs.
Build sheet
Craft 47 · Speed 91 · Volume 81 · Judgment 44 · Range 37 · Command 26
These are design settings, not test scores. Each dial changes how Hollis works, and the skill file says exactly how.
Token use
Light: about 8,000–23,000 tokens for a typical one-off job.
Learning
Steady learner: holds up to 34 lessons, learns one after 2 corrections. When full, Hollis asks which lesson to let go.
Working with others
Picks up one habit at a time from teammates, up to 2. 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 PHYSICIAN RECRUITER
- THE RECRUITER
- THE NURSE RECRUITER
- THE ALLIED HEALTH RECRUITER
- THE CONTEXT BUDGET CARD
The role
Core skills
- Job posts with pay
- Screening rubrics
- Résumé screens
- Candidate summaries
- Outreach
- Candidate updates
Typical assignments
- One-off · Write a job post and screen the applicantsFor example: Write a job post and rubric from a manager's notes, then screen 15 résumés and summarize the top five.
- Recurring · Running an open role's pipelineA typical batch: a 400-applicant pipeline.
Hands over
- a job post with the pay range
- a screening rubric
- candidate summaries for the hiring manager
How Hollis works
- Write the job from the real work, pay range on the face
- Build the rubric from stated requirements only
- Screen against the rubric; summarize evidence
- Draft outreach and updates; no one is ghosted
- Hand the shortlist to the human who decides
Standards
- Pay range in every post
- Screened only on job requirements
- Every candidate gets an answer
Works with
- lundr.tech skill cards: in its card slots, kept safe in your data center.
Lund Studio products only. Hollis works in Claude; these are the studio's own tools and cards it is built to use.
A hire, or an aiemployee
Budgeting for a hire in this job runs about $110,861 a year ($75,940 national median pay for human resources specialists, BLS, plus benefits). Hollis is bought once. An aiemployee doesn't replace the person; it drafts the work in Claude and someone at your company checks it.
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 Hollis stops
- Works only in Claude, on your own Claude account.
- Never makes a hiring, firing or pay decision. Screens on the job's stated requirements only, never on protected characteristics.
- 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.