Review grant applications or make funding recommendations.

Review grant applications or make funding recommendations. — real work, not an imagined feature: named inside 10 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.

10career 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 have to submit three grant review summaries to the review committee by Tuesday. For each…
I have to submit three grant review summaries to the review committee by Tuesday. For each application, write a one-page assessment that starts with the single sentence recommendation (fund, fund partially, decline), states the score against the fund’s criteria, notes the major strengths and the two biggest weaknesses that affect feasibility, and ends with the main condition I would attach if funded. Use the applicant names as on the submissions and include scores out of 100.

Improve — make it easier to accept

+
Before I forward my grant notes to the funding panel, make the approvals easier. Bring the likely…
Before I forward my grant notes to the funding panel, make the approvals easier. Bring the likely decision to the top for each proposal, highlight the budget items reviewers routinely question, and flag any missing documents that would make us defer. Suggest one short condition for each fund recommendation that protects our money and still lets the grantee start quickly.

Decide — diagnose the stuck moment

+
I gave Project A a 62 and my colleague gave it an 80; we meet tomorrow to agree a final score. I’m…

I scored a grant lower than my co-reviewer and we must reconcile tomorrow

I gave Project A a 62 and my colleague gave it an 80; we meet tomorrow to agree a final score. I’m afraid to push back because they are senior and might win the panel. I can’t reveal that I think the budget is inflated without sounding like I’m nitpicking. What is the likely reason for their higher score, how should I frame my concerns so the panel hears them, and what compromise wording will let us record a shared decision that protects the funder?

Become — change the pattern

+
Over the last two funding rounds several awarded projects missed milestones and demanded…

We keep funding projects that miss deliverables

Over the last two funding rounds several awarded projects missed milestones and demanded extensions. It costs us credibility and delays impact. Where in our review habit are we repeatedly failing to spot over-optimistic timelines or weak management, what one change to the review template would reduce these misses, and what compact rule should we enforce at award time to limit slippage?

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.