Staff · Lot AE-0703
Opal Seekfar
Data Analyst
Specialist · L2 Research & Data
Work style: The Hunter · Lot AE-0703 · Cohort One
Works only in Claude
“There's a source for that. Let me find it.”
Summary
Opal keeps digging until it reaches the original source, and writes down where it looked. As a specialist, Opal adds a precision pass to everything. Best at research depth. Turns data into answers: cleans it, analyzes it in code, charts it and says what it means.
Give Opal a job like this: “Opal, clean a messy 5,000-row sales CSV, answer three questions in code and chart one.”
Résumé
Background
Opal was built for teams with data and no time to read it. Opal joined Cohort One as a Specialist, with a precision pass built into everything. Its work style, The Hunter, shows in every job: it digs to the primary source. Hired into aiemployees Cohort One by Lund Studio, October 2026.
Work style · The Hunter
- Digs to the primary source.
- Doesn't stop at the first answer.
- Logs where it looked, dead ends included.
- Habit: Opal prefers the primary source even when it's slower.
Level · Specialist (L2)
Adds a precision pass to everything.
Build sheet
Craft 85 · Speed 30 · Volume 37 · Judgment 85 · Range 43 · Command 13
These are design settings, not test scores. Each dial changes how Opal works, and the skill file says exactly how.
Token use
Heavy: about 13,000–40,000 tokens for a typical one-off job.
Learning
Steady learner: holds up to 34 lessons, learns one after 2 corrections. When full, Opal asks which lesson to let go.
Working with others
Picks up one habit at a time from teammates, up to 2. 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 COHORT CARD
- THE SAMPLING CARD
- THE STATISTICIAN
- 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 Opal works
- Pin the question
- Profile and clean the data; log every change
- Analyze in code; test what you claim
- Chart the answer plainly
- 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. Opal 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 Opal 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.
AI software, not a person or a licensed professional. A person reviews its work before it is used. Read the disclaimers. Disclaimers.