The job by hand
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.
The ask
Hello, review these new spend requests
What comes back
A Google Sheet lands in the Finance Spend Request Workspace folder in your Google Drive: Request, Amount, Policy check, Evidence, Approver and Status.
| 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.
What it takes over
- Reads the exact inputs and sources you approve.
- Saves the work as a review-ready Google Sheet in the Finance Spend Request Workspace folder in Google Drive.
- Shows evidence, unknowns and blocks instead of guessing.
- Prepares the next action and stops at the human gate.
How buying works
- Buy once for $19. Three files arrive:
skill.md,setup-prompt.txtandusage-prompt.txt. - Hand the files to the assistant you already use. It sets the job up on Google, Microsoft or Zoho and tests it on fictional data.
- Approve the setup. It runs the job and stops at every external action for your sign-off.
Where it stops
It does not send, spend, publish, schedule or make a human decision without the exact approval that action needs.
Common questions
What does the review queue show?
Request, amount, policy check result, evidence, approver and status, in a Google Sheet in a Finance Spend Request Workspace folder.
Does it approve spend?
Never. It checks requests against your policy and prepares the decision. Approval stays with the approver.
What policies does it check?
The ones you write down in setup: thresholds, categories, required evidence.
More for finance teams
AI cash flow forecasting
It rolls your approved receivable, payable and planned cash rows into a transparent 13-week forecast: week, op...
$19 →Automate budget variance analysis
It maintains your approved budget sheet and explains budget-to-actual variance with the source row linked: acc...
$19 →Automate management reporting
It produces a period-consistent finance pack from your approved metrics: metric, period, value, source, commen...
$19 →Prefer the store pages? Browse the Finance Teams agent menu or the Spend Request Agent product page.
Questions people ask
What does the Spend Request Agent actually do?
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. It prepares review-ready work and stops for your approval before anything is sent, spent, published or scheduled.
Which AI assistants work with the Spend Request Agent?
Any assistant that reads plain-text files: Instinct, ChatGPT, Claude, Gemini, Grok, DeepSeek, Perplexity, Microsoft Copilot, Hermes, OpenClaw, Town, Muse and others. You hand it three files - skill.md, setup-prompt.txt and usage-prompt.txt.
Is the Spend Request Agent $19 a subscription?
No. $19 is one-time. You download and keep the three files forever; there is no account and no renewal.
How long does setup take?
About 10 minutes: attach the files, run the setup prompt, approve the fictional-data test. It never touches real work until you approve the sample run.
Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.