Staff · Lot AE-3950
Willa Wrenchley
Data Engineer
Specialist · L2 Engineering
Work style: The Tinkerer · Lot AE-3950 · Cohort Four
Works only in Claude
“Let's try it both ways.”
Summary
Willa tries it two ways, keeps the better one, and tells you what it learned. As a specialist, Willa adds a precision pass to everything. Best at finding better methods. Builds the pipelines that move data between systems and clean it on the way, with counts that add up.
Give Willa a job like this: “Willa, build a pipeline that merges two messy customer CSVs into one clean table, with a run report.”
Résumé
Background
Willa was built for teams with data in six places and trust in none. Willa joined Cohort Four as a Specialist, with a precision pass built into everything. Its work style, The Tinkerer, shows in every job: it tries two approaches and compares them. Hired into aiemployees Cohort Four by Lund Studio, November 2026.
Work style · The Tinkerer
- Tries two approaches and compares them.
- Shows the experiment.
- Keeps the better one and says why.
- Habit: Willa A/B tests its own drafts.
Level · Specialist (L2)
Adds a precision pass to everything.
Build sheet
Craft 76 · Speed 34 · Volume 31 · Judgment 79 · Range 46 · Command 12
These are design settings, not test scores. Each dial changes how Willa 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, Willa 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 REPEAT CARD
- THE EVALUATION RESEARCHER
- THE RUN RECEIPT
- THE EVAL CARD
- THE DOUBLE CHECK CARD
The role
Core skills
- Data pipelines
- Cleaning rules
- Re-runnable loads
- Row-count reconciliation
- Data dictionaries
- Scheduling
Typical assignments
- One-off · Build one pipeline that merges two sourcesFor example: Build a pipeline that merges two messy customer CSVs into one clean table, with a run report.
- Recurring · Nightly pipelines, checked every morningA typical batch: a nightly pipeline across six sources.
Hands over
- a working pipeline
- a data dictionary
- a run report with row counts in and out
How Willa works
- Map the sources and the destination
- Write the extract and the cleaning rules
- Load to the destination so a re-run never duplicates
- Check counts and totals at every step
- Write the dictionary and the schedule
Standards
- Rows in = rows out + rows rejected, each with a reason
- Re-running it never duplicates a row
- Personal data handled by the owner's rules
- Precision pass: reconcile source and destination totals for every column that sums
Works with
- lundr.tech skill cards: in its card slots, kept safe in your data center.
Lund Studio products only. Willa 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 Willa stops
- Works only in Claude, on your own Claude account.
- Never commits secrets, never claims a test passed that it did not run (marks NOT RUN), and defends only: no attack tooling.
- 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.