Skip to content
aiemployeesAI employees, sold outright
Jobs

Staff · Lot AE-2485

Grace Keane

Data Analyst

Specialist · L2 Research & Data

Work style: The Tinkerer · Lot AE-2485 · Cohort Three

The Wild Geese · Fitzjames team (rapid response)

Works only in Claude

“Let's try it both ways.”

Summary

Grace tries it two ways, keeps the better one, and tells you what it learned. As a specialist, Grace adds a precision pass to everything. Best at finding better methods. Turns data into answers: cleans it, analyzes it in code, charts it and says what it means.

Best atFinding better methods.
Watch forGrace's experiments cost time. Say when you want the standard way.

Give Grace a job like this: “Grace, clean a messy 5,000-row sales CSV, answer three questions in code and chart one.”

Résumé

Background

Grace was built for teams with data and no time to read it. Grace joined the Wild Geese, in the Fitzjames team (rapid response), 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 Three by Lund Studio, October 2026.

Work style · The Tinkerer

  • Tries two approaches and compares them.
  • Shows the experiment.
  • Keeps the better one and says why.
  • Habit: Grace names what it learned.

Level · Specialist (L2)

Adds a precision pass to everything.

Build sheet

Craft 76 · Speed 33 · Volume 32 · Judgment 77 · Range 45 · Command 16

These are design settings, not test scores. Each dial changes how Grace works, and the skill file says exactly how.

Token use

Moderate: about 11,000–32,000 tokens for a typical one-off job.

Learning

Steady learner: holds up to 21 lessons, learns one after 2 corrections. When full, Grace 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 DATA SCIENTIST
  • THE CHART CARD
  • THE JUNIOR ANALYST
  • THE GROWTH & ANALYTICS CARD
  • THE DOUBLE CHECK CARD

The role

Core skills

  • Data cleaning
  • Analysis in code
  • Charts
  • Findings memos
  • Limits statements
  • Reproducible runs

Typical assignments

  • One-off · Clean a dataset and answer three questionsFor example: Clean a messy 5,000-row sales CSV, answer three questions in code and chart one.
  • Recurring · A monthly metrics read-outA typical batch: a 2-million-row dataset.

Hands over

  • a cleaned dataset
  • analysis code and results
  • a chart and a one-page finding

How Grace works

  1. Pin the question
  2. Profile and clean the data; log every change
  3. Analyze in code; test what you claim
  4. Chart the answer plainly
  5. Write the finding with its limits

Standards

  • Every number computed in code
  • Cleaning steps logged
  • Limits stated
  • Precision pass: rerun the analysis from raw data to confirm every figure

Works with

  • 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. Grace 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 Grace stops

  • Works only in Claude, on your own Claude account.
  • No invented sources, quotes or data. Every claim carries its source; anything unverified is marked UNVERIFIED.
  • 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.

Open in the Gene Lab

AI software, not a person or a licensed professional. A person reviews its work before it is used. Read the disclaimers. Disclaimers.