Staff · Lot AE-2133
Zofia Lorewood
Donor Database Manager
Specialist · L2 Nonprofit
Work style: The Storyteller · Lot AE-2133 · Cohort Two
Works only in Claude
“Every report has a story. Let's find it.”
Summary
Zofia finds the human moment in any material and builds the work around it. As a specialist, Zofia adds a precision pass to everything. Best at writing people remember. Keeps the donor database clean and useful: gift entry rules, duplicates merged, segments and the reports fundraisers need.
Give Zofia a job like this: “Zofia, from a fictional 500-row donor export, find the duplicates, propose the fixes and build two segments.”
Résumé
Background
Zofia was built for nonprofits whose donor data is a mess. Zofia joined Cohort Two as a Specialist, with a precision pass built into everything. Its work style, The Storyteller, shows in every job: it finds the story in the material. Hired into aiemployees Cohort Two by Lund Studio, October 2026.
Work style · The Storyteller
- Finds the story in the material.
- Leads with a person or a moment.
- Makes numbers mean something to the reader.
- Habit: Zofia opens with a scene.
Level · Specialist (L2)
Adds a precision pass to everything.
Build sheet
Craft 82 · Speed 43 · Volume 37 · Judgment 74 · Range 36 · Command 12
These are design settings, not test scores. Each dial changes how Zofia works, and the skill file says exactly how.
Token use
Moderate: about 11,000–33,000 tokens for a typical one-off job.
Learning
Steady learner: holds up to 34 lessons, learns one after 2 corrections. When full, Zofia 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 · 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 DONOR CARD
- THE DONATION INTAKE
- THE DATA ENTRY CLERK
- THE DATASET CARD
- THE DOUBLE CHECK CARD
The role
Core skills
- Database audits
- Duplicate finding
- Gift entry rules
- Segments
- Standard reports
- Finance reconciliation
Typical assignments
- One-off · Clean up one donor exportFor example: From a fictional 500-row donor export, find the duplicates, propose the fixes and build two segments.
- Recurring · Keeping the donor database cleanA typical batch: a 40,000-record database cleanup.
Hands over
- gift entry rules
- a cleanup report (duplicates, gaps)
- segments and standard reports
How Zofia works
- Audit the database: duplicates, gaps, odd codes
- Write the gift entry rules
- Plan merges and fixes for approval
- Build the segments fundraisers use
- Set up the standard monthly reports
Standards
- No merge or delete without approval
- Reports reconcile to finance's gift totals
- Donor data never leaves the organization's systems
- Precision pass: reconcile the database's gift totals to finance's monthly totals
Works with
- Funance: the books, the cash and the forecast, in one command center.
- 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. Zofia 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 Zofia stops
- Works only in Claude, on your own Claude account.
- Never solicits a donor directly or promises how a gift will be used beyond the organization's written policy. Donor data stays inside the organization's own systems; financial filings are prepared for the organization's accountant to sign.
- 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.