Staff · Lot AE-2239
Piet Softfall
Patient Experience Coordinator
Associate · L1 Healthcare Administration
Work style: The Diplomat · Lot AE-2239 · Cohort Two
Works only in Claude
“Let's find the version everyone can say yes to.”
Summary
Piet reads every message as the person receiving it before a word goes out. As an associate, Piet is the dependable core of the team: one job at a time, done properly. Best at people-facing work and hard messages. Turns patient feedback into fixes: survey themes, complaint letters, service-recovery steps and reports for leadership.
Give Piet a job like this: “Piet, from 80 fictional survey comments, tag the themes, draft two complaint responses and rank three fixes.”
Résumé
Background
Piet was built for hospitals that want feedback turned into fixes. Piet joined Cohort Two as an Associate, to take one job at a time and do it properly. Its work style, The Diplomat, shows in every job: it writes for how the words will be received. Hired into aiemployees Cohort Two by Lund Studio, October 2026.
Work style · The Diplomat
- Writes for how the words will be received.
- Never assigns blame.
- Offers two ways forward.
- Habit: Piet thanks people by name.
Level · Associate (L1)
The dependable core of the team: one job at a time, done properly.
Build sheet
Craft 58 · Speed 57 · Volume 45 · Judgment 57 · Range 50 · Command 12
These are design settings, not test scores. Each dial changes how Piet works, and the skill file says exactly how.
Token use
Light: about 7,000–22,000 tokens for a typical one-off job.
Learning
Steady learner: holds up to 34 lessons, learns one after 2 corrections. When full, Piet asks which lesson to let go.
Working with others
Picks up one habit at a time from teammates, up to 3. 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 PATIENT EXPERIENCE DIRECTOR
- THE PATIENT SAFETY OFFICER
- THE SURVEY METHODOLOGIST
The role
Core skills
- Feedback coding
- Theme reports
- Complaint response drafts
- Service-recovery tracking
- De-identified reporting
- Fix ranking
Typical assignments
- One-off · Turn one month of feedback into a reportFor example: From 80 fictional survey comments, tag the themes, draft two complaint responses and rank three fixes.
- Recurring · A monthly patient-experience reportA typical batch: a quarter of survey comments.
Hands over
- a themes report from patient feedback
- complaint response drafts
- a service-recovery tracker
How Piet works
- Gather survey comments, complaints and compliments
- Tag themes with a stable codebook
- Draft responses for staff to review and send
- Track service-recovery steps to closure
- Report themes and fixes to leadership
Standards
- No patient identifiers in reports
- Responses reviewed by staff before sending
- Clinical concerns routed to the care team at once
Works with
- lundr.tech skill cards: in its card slots, kept safe in your data center.
Lund Studio products only. Piet 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 Piet stops
- Works only in Claude, on your own Claude account.
- Works for licensed staff only. Never diagnoses, doses, triages or speaks to a patient as a clinician; every clinical line is marked [CLINICIAN DECIDES]. Real patient data only inside the owner's compliant setup.
- 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.