Way 1: without AI (the manual way)
Honest cost: 10-15 minutes per request, plus audit pain later.
- Read each request from email, chat or hallway.
- Check it against policy: threshold, category, evidence.
- Route to the right approver and record the decision.
Approving spend over chat means audit season becomes archaeology. The method below runs intake with an assistant: structure each request, check it against the policy you provide, list missing evidence, and draft the approval or the questions - with the decision and its reasons recorded per request.
Pros of doing it manually
- Free except your time - no tools, no accounts.
- You learn the job deeply and control every detail.
- No data leaves your hands.
Cons of doing it manually
- 10-15 minutes per request, plus audit pain later - every single time the job runs.
- Quality depends on your energy that day.
- More volume just means more hours; it does not scale.
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:
- You must paste the policy rules every run - the model does not remember your thresholds.
- You must keep approval strictly human; a loose prompt will start "approving" things.
- You must build your own audit trail, or audit season is archaeology.
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
- Free, or nearly - any chat assistant works.
- A first draft in minutes instead of hours.
- Fully flexible: tweak the prompt for any edge case.
Cons of DIY prompting
- You become the workflow designer: prompts, test data and output rules are yours to write, test and maintain.
- Output drifts between sessions unless you re-paste the rules every run.
- Nothing is saved for you - sheets, structure and context are rebuilt each time.
Way 3: with AI Agent Skills (free, Free)
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:
| Request | Amount | Policy check | Evidence | Approver | Status |
|---|---|---|---|---|---|
| Figma renewal (Design) | $540/yr | Under $1k software threshold - manager approval only | Invoice attached, matches last year's seat count | Priya (Eng manager) | Approved |
| New analytics tool | $4,800/yr | Over $1k - needs finance lead sign-off | Quote attached; no security review on file | Unassigned | Blocked - security review needed |
Sample data shown. Your workspace fills with your real work.
Setup takes about 10 minutes: download, hand the Included 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
- About 10 minutes to a tested setup, not an afternoon of prompt tuning.
- The same output shape every run - evidence rules and stop points are already designed.
- Runs on a standing cycle or a one-line ask; files land in your own Drive.
Cons of the ready-made agent
- Costs free, where DIY prompting is free.
- The output format is opinionated - you adapt the template rather than rebuild it.
- It still stops and waits for your approval at decision points; it is not zero-touch.
The honest comparison
| Way 1: manual | Way 2: DIY AI | Way 3: free agent | |
|---|---|---|---|
| Time to first result | 10-15 minutes per request, plus audit pain later | An afternoon of prompt tuning | About 10 minutes, tested setup |
| Every run after | Same hours, every time | Re-paste the rules, sheet and context each run | One short ask, or a standing cycle |
| Consistency | Depends on the day | Drifts between sessions | Same output shape every run |
| Cost | Your hours | Free, plus your time | Free, 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 free 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 free 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.