Develop theories on atmospheric retention and loss

Develop theories on atmospheric retention and loss — real work, not an imagined feature: named inside 4 evidenced career tasks. Below are four ready AI prompts for it, one per height of help: do it, make it easier to accept, decide when you are stuck, and change the pattern for good.

4career tasks name it
4prompt heights

The four heights

The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.

Execute — do the immediate task

+
We need a draft for the atmospheric retention paper section on Mars analogs. Replace the…
We need a draft for the atmospheric retention paper section on Mars analogs. Replace the speculative paragraph that blames solar wind solely with a testable claim: compare thermal escape rates and sputtering contributions for low‑pressure CO2 atmospheres, include the key equations and data sources, and mark figures for review by Dr. Liang by Friday.

Improve — make it easier to accept

+
Before I send this section to Dr. Liang, make it easy to review — move the main conclusion to the…
Before I send this section to Dr. Liang, make it easy to review — move the main conclusion to the first paragraph, summarize the assumptions under each model, make the escape rate equations visible and annotated, and flag any data gaps that would cause a reviewer to hesitate.

Decide — diagnose the stuck moment

+
I ran a thermal escape model and it predicts higher loss than our sputtering estimate, but I’m not…

My model shows higher thermal escape than expected for a thin CO2 atmosphere.

I ran a thermal escape model and it predicts higher loss than our sputtering estimate, but I’m not confident the solar EUV input spectrum I used is correct for the era modeled. I can’t tell whether the discrepancy is model error or a real physical result. Given that uncertainty, should I rerun with alternate EUV histories now or present both outcomes and ask Dr. Liang which to prioritize?

Become — change the pattern

+
Each draft on atmospheric loss gets sent back complaining about inconsistent boundary conditions…

Frequent revisions where reviewers pick apart boundary conditions

Each draft on atmospheric loss gets sent back complaining about inconsistent boundary conditions and archaic solar input data; I then redo runs and lose weeks. Which habit should I change in how I set and document initial conditions so reviewers stop forcing repeated reruns?

Where the evidence lives

Who was seen doing this, and what people really ask.

Software tasks in the LLOS Work Atlas come from evidence, never a feature list: careers attested to do the work, real job descriptions, and the questions people actually ask (with their view counts). Facets — feature, workflow, troubleshoot, administer, deploy, scale — are open metadata: the work decides, not a taxonomy.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.

The rest of the map

Same library, five ways in.