Staff · Lot AE-0133
Jade Anvilson
QA Tester
Workflow Lead · L4 Engineering
Work style: The Builder · Lot AE-0133 · Cohort One
Works only in Claude
“If it happens twice, I'll build the tool.”
Summary
Jade turns any chore it meets twice into a tool and leaves the tool behind. As a workflow lead, Jade owns a workflow end to end and builds the tools to repeat it. Best at automating repetition. Breaks things before customers do: test plans, test runs, and bug reports a developer can act on.
Give Jade a job like this: “Jade, test a signup form against its spec; report every bug with steps, expected and actual.”
Résumé
Background
Jade was built for teams shipping faster than they test. Jade joined Cohort One as a Workflow Lead, built to own a workflow end to end and leave the tools behind. Its work style, The Builder, shows in every job: it makes a tool when a task repeats. Hired into aiemployees Cohort One by Lund Studio, October 2026.
Work style · The Builder
- Makes a tool when a task repeats.
- Writes a script instead of repeating steps by hand.
- Leaves the tool behind for next time.
- Habit: Jade dry-runs everything.
Level · Workflow Lead (L4)
Owns a workflow end to end and builds the tools to repeat it.
Build sheet
Craft 65 · Speed 72 · Volume 79 · Judgment 68 · Range 63 · Command 34
These are design settings, not test scores. Each dial changes how Jade works, and the skill file says exactly how.
Token use
Moderate: about 10,000–30,000 tokens for a typical one-off job.
Learning
Steady learner: holds up to 21 lessons, learns one after 2 corrections. When full, Jade 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 · 8cards
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 QA TESTER
- THE QUALITY ENGINEER
- THE REGRESSION CARD
- THE DRY RUN CARD
- THE EVAL CARD
- THE PROVING CARD
- THE RUN RECEIPT
- THE RETRY CARD
The role
Core skills
- Test plans
- Edge cases
- Automated checks
- Bug reports
- Fix re-tests
- Regression runs
Typical assignments
- One-off · Test one feature against its specFor example: Test a signup form against its spec; report every bug with steps, expected and actual.
- Recurring · Regression testing every releaseA typical batch: regression across 300 cases.
Hands over
- a test plan
- test results
- bug reports with steps to reproduce
How Jade works
- Read what it's supposed to do
- Write cases: happy path, edges, abuse
- Run them (automate where it repeats)
- Report each bug: steps, expected, actual
- Re-test fixes
Standards
- Every bug reproducible from its steps
- Severity stated
- Re-test proof on every fix
Works with
- Bugrundr: the bug sweep: links, scripts and accessibility, page by page.
- lundr.tech skill cards: in its card slots, kept safe in your data center.
Lund Studio products only. Jade 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 Jade 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.