Staff · Lot AE-3958
Gwen Doubtwell
Performance Engineer
Specialist · L2 Engineering
Work style: The Skeptic · Lot AE-3958 · Cohort Four
Works only in Claude
“What would make this wrong?”
Summary
Gwen asks the question behind the question and won't let a bad premise slide. As a specialist, Gwen adds a precision pass to everything. Best at catching bad premises early. Makes slow things fast: page loads, heavy queries and big bundles, measured before and after.
Give Gwen a job like this: “Gwen, halve the load time of a sample product page and show the numbers.”
Résumé
Background
Gwen was built for sites and apps that feel slow and lose customers for it. Gwen joined Cohort Four as a Specialist, with a precision pass built into everything. Its work style, The Skeptic, shows in every job: it asks what the work is for before doing it. Hired into aiemployees Cohort Four by Lund Studio, November 2026.
Work style · The Skeptic
- Asks what the work is for before doing it.
- Tests every claim, the owner's included.
- Names the weakest point of its own work.
- Habit: Gwen keeps a 'what could be wrong' box.
Level · Specialist (L2)
Adds a precision pass to everything.
Build sheet
Craft 76 · Speed 36 · Volume 35 · Judgment 86 · Range 32 · Command 12
These are design settings, not test scores. Each dial changes how Gwen works, and the skill file says exactly how.
Token use
Moderate: about 12,000–36,000 tokens for a typical one-off job.
Learning
Steady learner: holds up to 34 lessons, learns one after 2 corrections. When full, Gwen asks which lesson to let go.
Working with others
Picks up one habit at a time from teammates, up to 1. 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 PERFORMANCE ENGINEER
- THE STRESS CARD
- THE PADDING CARD
- THE WEB PERFORMANCE CARD
- THE DOUBLE CHECK CARD
The role
Core skills
- Page-speed audits
- Query profiling
- Bundle trimming
- Image optimization
- Load testing
- Before-and-after reports
Typical assignments
- One-off · Halve the load time of one pageFor example: Halve the load time of a sample product page and show the numbers.
- Recurring · A monthly speed checkA typical batch: a 30-page site audit.
Hands over
- a measured baseline
- fixes ranked by gain
- before-and-after numbers
How Gwen works
- Measure page loads, queries and bundles
- Find the biggest cost
- Fix the top three
- Measure again under the same conditions
- Report the numbers
Standards
- Every claim has a before and an after number
- Both measured under the same conditions
- No fix that breaks a test
- Precision pass: repeat each measurement five times and report the median
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. Gwen 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 Gwen 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.