Guide · 3 ways compared

How to review spend requests against policy as a finance lead

There are three honest ways to review spend requests against policy: manually (about 10-15 minutes per request, plus audit pain later), with DIY AI prompting, or with a $19 ready-made agent. This guide compares all three with real pros and cons.

It normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status. Approvals become one review, not a reconstruction. Here are the three honest ways to get it done, with real trade-offs.

Way 1: without AI (the manual way)

Honest cost: 10-15 minutes per request, plus audit pain later.

  1. Read each request from email, chat or hallway.
  2. Check it against policy: threshold, category, evidence.
  3. Route to the right approver and record the decision.

Spend requests arrive by email, chat and the occasional hallway ask. Policy checks happen in someone's head, and audit season reconstructs decisions nobody wrote down.

Pros of doing it manually

Cons of doing it manually

Way 2: with AI, but without AI Agent Skills (DIY prompting)

A chat assistant genuinely helps here. The catch is that you become the workflow designer. What you have to figure out yourself:

Here is a starter prompt that works - copy it and bring the inputs listed:

Check these spend requests against our policy: [paste requests, then policy rules]. Per request: pass/fail/unclear per rule, missing evidence, and the approver level it routes to. Do not approve or reject - that decision belongs to the approver.

More on this prompt: the free spend request approvals prompt page.

Pros of DIY prompting

Cons of DIY prompting

Way 3: with AI Agent Skills ($19, one-time)

The Spend Request Agent is this job already designed: fixed evidence rules, output contract, test fixtures and stop points. You ask once:

Hello, review these new spend requests

And a finished, review-ready artifact lands in your own Drive:

RequestAmountPolicy checkEvidenceApproverStatus
Figma renewal (Design)$540/yrUnder $1k software threshold - manager approval onlyInvoice attached, matches last year's seat countPriya (Eng manager)Approved
New analytics tool$4,800/yrOver $1k - needs finance lead sign-offQuote attached; no security review on fileUnassignedBlocked - security review needed

Sample data shown. Your workspace fills with your real work.

Setup takes about 10 minutes: buy, hand the three files to the assistant you already use (Instinct, ChatGPT, Claude, Gemini or any other assistant that reads files), approve the fictional-data test. Then it runs on a standing cycle or a one-line ask, and stops at every human gate. Full method.

Pros of the ready-made agent

Cons of the ready-made agent

Get the Spend Request Agent · $19

The honest comparison

Way 1: manualWay 2: DIY AIWay 3: $19 agent
Time to first result10-15 minutes per request, plus audit pain laterAn afternoon of prompt tuningAbout 10 minutes, tested setup
Every run afterSame hours, every timeRe-paste the rules, sheet and context each runOne short ask, or a standing cycle
ConsistencyDepends on the dayDrifts between sessionsSame output shape every run
CostYour hoursFree, plus your time$19 once, files kept forever

The manual way teaches you the job. DIY prompting is fine for a one-off. The agent wins when the job repeats every week.

More: the Spend Request Agent product page · the spend request approvals guide · AI agents for finance teams

Questions people ask

What is the fastest way to review spend requests against policy?

The $19 ready-made agent: about 10 minutes of setup, then one short ask per run. Manual takes 10-15 minutes per request, plus audit pain later; DIY prompting takes an afternoon of tuning plus upkeep.

Can I review spend requests against policy without AI?

Yes - the manual steps are on this page. Expect 10-15 minutes per request, plus audit pain later each time the job runs.

Is the $19 agent worth it over DIY prompting?

If the job repeats weekly, yes: you stop rebuilding prompts and re-pasting context every run. For a one-off, DIY prompting is fine and free.

Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.