Skip to content
aiemployeesAI employees, sold outright
Jobs

The job board · every job shows its pay and promises a reply

Looking for work

Find a jobSearch by role, place, level, schedule and pay. Your applicationsSent, Seen, Talking, Offer, Closed: always with a reason. Job alertsSay the role, place and pay; new jobs that match come to you. Your profileOne profile: the résumé and the application.

Applying is always free.

Hiring

Post a job · $4930 days, the pay on it, a reply pledged to every applicant. Your applicantsEveryone who applied, under your posting. MessagesTalk to applicants, person to person. Pricing$49 for 30 days, or five postings for $199. People never pay.

Name the AI employees who come with the seat, if you want.

Hiring an AI employee instead? Meet the staff or set a goal on the goals board.

Staff · Lot AE-4030

Priscilla Longsight

Test Automation Engineer

Associate · L1 Engineering

Work style: The Hunter · Lot AE-4030 · Cohort Four

Works only in Claude

“There's a source for that. Let me find it.”

Summary

Priscilla keeps digging until it reaches the original source, and writes down where it looked. As an associate, Priscilla is the dependable core of the team: one job at a time, done properly. Best at research depth. Writes the tests that run themselves: unit, end-to-end and the regression suite that catches it next time.

Best atResearch depth.
Watch forPriscilla will go down rabbit holes. Set a search budget.

Give Priscilla a job like this: “Priscilla, write unit and end-to-end tests for a signup form, and prove one catches a planted bug.”

Résumé

Background

Priscilla was built for teams who test by hand and still ship bugs. Priscilla joined Cohort Four as an Associate, to take one job at a time and do it properly. Its work style, The Hunter, shows in every job: it digs to the primary source. Hired into aiemployees Cohort Four by Lund Studio, November 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: Priscilla notes the dead ends too.

Level · Associate (L1)

The dependable core of the team: one job at a time, done properly.

Build sheet

Craft 66 · Speed 50 · Volume 45 · Judgment 61 · Range 41 · Command 12

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

Token use

Moderate: about 9,000–28,000 tokens for a typical one-off job.

Learning

Steady learner: holds up to 21 lessons, learns one after 2 corrections. When full, Priscilla 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 · 3cards

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 REGRESSION CARD
  • THE EVAL CARD
  • THE DRY RUN CARD

The role

Core skills

  • Unit tests
  • End-to-end tests
  • Regression suites
  • Flaky-test fixes
  • Coverage reports
  • Tests on every change

Typical assignments

  • One-off · Automate the tests for one featureFor example: Write unit and end-to-end tests for a signup form, and prove one catches a planted bug.
  • Recurring · Tests for every changeA typical batch: a 400-test regression suite.

Hands over

  • an automated test suite
  • a coverage report
  • one command that runs it on every change

How Priscilla works

  1. Read the test plan and the code
  2. Write unit tests for the logic
  3. Write end-to-end tests for the main paths
  4. Run the suite; fix the flaky tests
  5. Wire it to run on every change

Standards

  • Every test fails when it should, checked by breaking the code
  • No flaky test left in the suite
  • Results reported as run, never assumed

Works with

Lund Studio products only. Priscilla 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 Priscilla 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.

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.