Discover new food sources

Discover new food sources — real work, not an imagined feature: named inside 7 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.

7career 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

+
I need a sheet listing novel edible plants we might trial this season, with columns for species,…
I need a sheet listing novel edible plants we might trial this season, with columns for species, source, growing zone, yield estimate per square metre, taste notes, processing requirements, allergen flags, and first test batch date. Put rows for five candidate species we already discussed: Perennial grain, duckweed strain L-3, breadfruit cultivar ‘Mihi’, sacha inchi, and moringa; sort by earliest feasible test date and highlight any with processing hazards.

Improve — make it easier to accept

+
Before I share the candidate list with Rina in R&D and Tomas in Operations, make the results easy…
Before I share the candidate list with Rina in R&D and Tomas in Operations, make the results easy to act on: show an upfront column called ‘Immediate blocker’ that names the single thing that would stop a trial (seed availability, permit, unusual processing), move yield and processing time to the left, and flag anything needing lab analysis in red so Rina can approve quickly.

Decide — diagnose the stuck moment

+
I ran germination and yield estimates for five new food crops and three of them have very wide…

I just ran germination estimates and several species show wildly different yield ranges

I ran germination and yield estimates for five new food crops and three of them have very wide yield ranges that change feasibility. Rina in R&D trusts lab numbers; Tomas in Operations will refuse anything that needs special drying. I don’t know which uncertainty to escalate and what to present to procurement for seed orders. Recommend the likeliest cause, which numbers I should freeze for a go/no-go, and the best one-paragraph summary to send to Rina and Tomas.

Become — change the pattern

+
Across ten seasons we lose time reconciling yield, processing and allergen notes because every…

We keep redoing trial sheets because yields and processing notes scatter across files

Across ten seasons we lose time reconciling yield, processing and allergen notes because every analyst makes their own column names and stores raw lab results in separate files. Suggest one habit change to stop rework and speed decisions: describe the single canonical sheet layout we should require, who enforces it, and a practical rule for one-line lab result entries so Operations can read a go/no-go in under 30 seconds.

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.