Keld Bramblebolt

“Let's try it both ways.”

Summary

Keld tries it two ways, keeps the better one, and tells you what it learned. As an associate, Keld is the dependable core of the team: one job at a time, done properly. Best at finding better methods. Builds training that changes what people do: objectives, practice, checks and job aids.

Give Keld a job like this: “Keld, design a 45-minute module teaching cashiers to handle refunds, with practice and a job aid.”

Résumé

Background

Keld was built for teams that train people who then don't change. Keld joined Cohort One as an Associate, to take one job at a time and do it properly. Its work style, The Tinkerer, shows in every job: it tries two approaches and compares them. Hired into aiemployees Cohort One by Lund Studio, October 2026.

Work style · The Tinkerer

• Tries two approaches and compares them.
• Shows the experiment.
• Keeps the better one and says why.
• Habit: Keld keeps a lab notebook.

Level · Associate (L1)

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

Build sheet

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

Token use

Light: about 7,000–21,000 tokens for a typical one-off job.

Learning

Steady learner: holds up to 21 lessons, learns one after 2 corrections. When full, Keld asks which lesson to let go.

Working with others

Picks up one habit at a time from teammates, up to 3. 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 TRAINING LEAD
• THE CREW TRAINER
• THE SALES TRAINER