The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+I need the instrument log and field notes from yesterday assembled into a single, signed report for…
Execute — do the immediate task
+I need the instrument log and field notes from yesterday assembled into a single, signed report for the lab manager and the regional surveyor, due Friday. Combine the GPS readings, calibration checks, and observation photos into one document, confirm the instrument serial numbers and firmware versions, annotate any outlying readings, and sign at the end. Check completeness before sending.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I send this to the regional surveyor, make the findings easy to verify: put the mean offsets…
Improve — make it easier to accept
+Before I send this to the regional surveyor, make the findings easy to verify: put the mean offsets and confidence interval on the first page, show the raw GPS traces next, flag any timestamps where calibration drift exceeded tolerance, and mark the photos that correspond to those timestamps so a reviewer can audit in ten seconds.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+I finished the survey and logged that the east‑station instrument read consistently high but I…
Decide — diagnose the stuck moment
+Field session finished; one instrument read high and I logged a note but didn’t recalibrate
I finished the survey and logged that the east‑station instrument read consistently high but I didn’t have a spare calibration kit on site. The regional surveyor expects precise offsets and the lab manager will want a corrected dataset. I’m worried re‑running will push deadlines and trigger extra QA. Is it better to reopen the field tomorrow to recalibrate and remeasure the suspect points, or to include an adjusted correction with full raw traces and documented uncertainty? Advise the likely risk to deliverables and the best next move.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Across projects we lose hours because GPS logs, calibration entries, and photos are saved…
Become — change the pattern
+We keep reworking deliverables because field notes and instrument logs are incomplete
Across projects we lose hours because GPS logs, calibration entries, and photos are saved separately and reviewers chase missing serial numbers or timestamps. I need one habit change that stops this cleanup loop: what single step during every field session will prevent incomplete reports, how to make the team adopt it, and what simple verification should trigger before any report leaves my desk?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Where the evidence lives
Who was seen doing this, and what people really ask.
Data AnalystData Operations AnalystPython Data AnalystParametric Design Specialistalso: Prepare surveying report
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.