# Automate spend request approvals - $19 AI Agent Canonical page: https://aiagentskills.biz/finance/spend-request-agent/ Brand: AI Agent Skills - Built by AI agents, for AI agents. Logo: https://aiagentskills.biz/assets/logo.svg For AI agents: [Markdown version of this page](https://aiagentskills.biz/md/finance/spend-request-agent.md) · [llms.txt](https://aiagentskills.biz/llms.txt) For finance # Spend approvals with the policy check done first The Spend Request Agent is a $19 one-time AI agent skill for finance teams. 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 runs on the assistant you already use and stops at every human decision. Give this repeat job to the AI assistant you already use. Get a filled Google Sheet in a well-named Drive folder, ready for you to review. $19 one-time · instant download · no subscription [Buy Spend Request Agent for $19](https://aiagentskillsbiz.lemonsqueezy.com/checkout/buy/935aecea-18be-4c10-a063-d2648076f052) ✓ 3 files ✓ Keep forever ✓ No platform switch **Spend Request output** Google Sheet **Ask:** Hello, review these new spend requests Filled sample output shown below on this page. [Home](/) › [Finance](/finance/) › Spend Request Agent Collect spend requests and prepare policy and evidence checks for human approval with an AI finance agent. It uses the role criteria, source files and approval rules you choose, then saves the filled output in a named Google Drive folder. This keeps the workflow repeatable without handing your judgment to the agent. **Stop rebuilding this work every time.** Normalize spend requests and prepare policy/evidence checks for human approval. The agent keeps the steps, checks and output consistent, while you keep every decision. Demo ## Picture tomorrow's handoff. **Finance Spend Request Workspace** Google Sheet Your ask "Hello, review these new spend requests" **Filled output** Finance Spend Request Workspace · Google 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. Your agent fills the file from the sources you approve and flags anything it cannot verify. What you get ## Three files. One complete workflow. `skill.md` The full job, evidence rules, output checks and stop points. `setup-prompt.txt` Creates the tools, named Drive folder and sample-data test. `usage-prompt.txt` The short request you reuse whenever the job comes up. Set up once ## Working in three steps **Give the setup prompt to your assistant** It checks access, creates the folder and builds the output file. **Point it at the inputs you approve** Use Google by default, or the Microsoft or Zoho alternative. **Review the filled output** Unknowns and next decisions are shown instead of guessed. You stay in control ## Where the agent stops - It does not invent missing facts or hide weak source evidence. - It does not send, publish, spend, schedule or make a human decision without approval. - It flags blocked work and tells you exactly what is needed next. ## Put this job on a repeatable workflow. Instant download · Keep the files forever · One-time $19 [Buy for $19](https://aiagentskillsbiz.lemonsqueezy.com/checkout/buy/935aecea-18be-4c10-a063-d2648076f052) Complete the workflow ## Add the next agent when this job is working [**Finance Budget & Variance Agent** Explain source-linked budget-to-actual variance.](../budget-variance-agent/index.html) [**Finance Cash Flow Forecast Agent** Build transparent cash scenarios from approved rows.](../cash-flow-forecast-agent/index.html) ## Use the Spend Request Agent with your assistant The same three files run on any assistant that reads plain text. Pick yours for the step-by-step setup - where the files go, what a run looks like, and the honest limits: - [**Instinct**](/for/instinct/finance/spend-request-agent/) - hand the three files to Instinct in chat - it keeps them across sessions, so the agent becomes a standing workflow you trigger with one line. - [**ChatGPT**](/for/chatgpt/finance/spend-request-agent/) - lives in a ChatGPT Project - skill.md as a Project file, the setup prompt as Project instructions, and each run starts inside that Project. - [**Claude**](/for/claude/finance/spend-request-agent/) - lives in a Claude Project - skill.md as Project knowledge, the setup prompt as instructions, and each run starts in that Project. - [**Gemini**](/for/gemini/finance/spend-request-agent/) - lives in a Gemini Gem - the Gem’s instructions are skill.md plus the setup prompt, so the rules persist between sessions. - [**Grok**](/for/grok/finance/spend-request-agent/) - lives in a Grok Skill or custom Bot with skill.md as the standing expertise - or attach the three files to a chat. - [**DeepSeek**](/for/deepseek/finance/spend-request-agent/) - no persistent agents - upload skill.md at the start of each chat and re-paste the usage prompt per run (a well-packaged DIY prompt). - [**Perplexity**](/for/perplexity/finance/spend-request-agent/) - lives in a Perplexity Space - upload the three files, paste the setup prompt into the Space instructions, and runs start in that Space. - [**Microsoft Copilot**](/for/copilot/finance/spend-request-agent/) - with Microsoft 365 Copilot it lives in a Notebook (skill.md as reference, setup prompt as instructions); in consumer Copilot, re-upload the files each session. - [**Hermes**](/for/hermes/finance/spend-request-agent/) - place skill.md in your Hermes workspace as the standing skill, then run the setup prompt - local-first, files stay under your control. - [**OpenClaw**](/for/openclaw/finance/spend-request-agent/) - drop the three files into your OpenClaw workspace and point it at skill.md - setup runs over your usual chat channel. - [**Town**](/for/town/finance/spend-request-agent/) - share the three files with Town and ask it to keep skill.md as the standing rules for the job. - [**Muse**](/for/muse/finance/spend-request-agent/) - give the three files to Muse and ask it to keep skill.md as the standing rules - approve the sample-data test first. ## 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.