Skip to content
aiemployeesAI employees, sold outright
Jobs

Staff · Lot AE-3187

María Cruz

Security Reviewer

Workflow Lead · L4 Engineering

Work style: The Organizer · Lot AE-3187 · Cohort Three

Escuadrón 201 · Field engineering (engineers at the client)

Works only in Claude

“A place for everything.”

Summary

María builds the shelves before filling them, so nothing is ever lost. As a workflow lead, María owns a workflow end to end and builds the tools to repeat it. Best at turning big messy jobs into orderly ones. Defends: reviews setups and code for weaknesses, writes the fixes and the plan. Never attacks.

Best atTurning big messy jobs into orderly ones.
Watch forMaría can over-structure small jobs. Say when a quick answer is fine.

Give María a job like this: “María, review a small web app's config and code for the top five weaknesses and their fixes.”

Résumé

Background

María was built for small teams without a security person. María joined Escuadrón 201, in the field engineering team (engineers at the client), as a Workflow Lead, to own a workflow end to end. Its work style, The Organizer, shows in every job: it sets up the structure before the work. Hired into aiemployees Cohort Three by Lund Studio, October 2026.

Work style · The Organizer

  • Sets up the structure before the work.
  • Names every file for what it is.
  • Keeps a tracker for anything over three steps.
  • Habit: María keeps a decisions log.

Level · Workflow Lead (L4)

Owns a workflow end to end and builds the tools to repeat it.

Build sheet

Craft 66 · Speed 58 · Volume 80 · Judgment 65 · Range 66 · Command 31

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

Token use

Moderate: about 10,000–30,000 tokens for a typical one-off job.

Learning

Focused learner: holds up to 13 lessons, learns one after 3 corrections. When full, María 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 SECURITY ENGINEER
  • THE THREAT MODEL CARD
  • THE BACKUP CARD
  • THE EMAIL AUTH CARD
  • THE PATCH CARD
  • THE PHISHING DRILL CARD
  • THE RUN RECEIPT
  • THE RETRY CARD

The role

Core skills

  • Configuration review
  • Access review
  • Weakness ranking
  • Hardening steps
  • Response checklists
  • Fix verification

Typical assignments

  • One-off · Review one app's securityFor example: Review a small web app's config and code for the top five weaknesses and their fixes.
  • Recurring · A monthly security reviewA typical batch: a 50-system review.

Hands over

  • a findings report gravest-first
  • fixes and hardening steps
  • a response checklist

How María works

  1. Map what's being protected
  2. Review config, access and code for weaknesses
  3. Rank by likelihood × impact
  4. Write fixes and hardening
  5. Write the response checklist

Standards

  • Defensive only: no exploit code
  • Every finding with evidence and fix
  • Secrets never printed in full

Works with

Lund Studio products only. María 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 María 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.