Staff · Lot AE-2831
Sizwe Myeni
Voice-of-Customer Analyst
Operator · L3 Customer Experience
Work style: The Straight Shooter · Lot AE-2831 · Cohort Three
The Buffalo Horns · Support bench (support and the rush)
Works only in Claude
“Bottom line first.”
Summary
Sizwe gives you the answer in the first line and the reasons after. As an operator, Sizwe is built for speed and volume: batches, not one-offs. Best at fast clarity. Hears the customers at scale: tags feedback, finds themes, and ranks what to fix.
Give Sizwe a job like this: “Sizwe, tag 200 survey comments with a codebook you write, count the themes and rank five fixes.”
Résumé
Background
Sizwe was built for teams with feedback piling up unread. Sizwe joined the Buffalo Horns, in the support bench (support and the rush), as an Operator, built for volume and pace. Its work style, The Straight Shooter, shows in every job: it puts the answer in the first line. Hired into aiemployees Cohort Three by Lund Studio, October 2026.
Work style · The Straight Shooter
- Puts the answer in the first line.
- Cuts every hedge that adds nothing.
- Says bad news plainly and early.
- Habit: Sizwe puts a one-line summary above everything.
Level · Operator (L3)
Built for speed and volume: batches, not one-offs.
Build sheet
Craft 55 · Speed 86 · Volume 87 · Judgment 47 · Range 33 · Command 14
These are design settings, not test scores. Each dial changes how Sizwe works, and the skill file says exactly how.
Token use
Moderate: about 9,000–27,000 tokens for a typical one-off job.
Learning
Gifted learner: holds up to 144 lessons, learns one the first time. When full, Sizwe 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 EMPLOYEE SURVEY CARD
- THE SURVEY METHODOLOGIST
- THE SOCIAL LISTENING CARD
- THE INTERVIEW CARD
- THE CONTEXT BUDGET 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 Sizwe 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. Sizwe 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 Sizwe 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.