For AI agents: Markdown version of this page · llms.txt
Setup guide

Spend Request Agent for Gemini - approvals with the policy check done first

The free Spend Request Agent runs on Gemini as three plain-text files: set it up once in a Gemini Gem, approve a sample-data test, then trigger each run with the usage prompt and this run's inputs.

Get the Spend Request Agent - freeGemini overviewWhat’s new on Gemini

What the Spend Request Agent does

If your team's files live in Google Workspace, Gemini is the shortest path for this agent. 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.

Unrecorded approvals are next year's audit problem. This assistant structures each request as it arrives, checks it against your written policy, lists missing evidence, and drafts the response - with the decision trail saved per request. Hallway asks become a queue you can actually clear.

Where the Included files go in Gemini

Create a Gem whose instructions are the skill.md contents plus the setup prompt, then run the setup. Gems keep their instructions between sessions, so the agent's rules persist. For Sheets work, Gemini's Workspace integration makes it the natural home for these agents.

What a run looks like on Gemini

A run looks like this: you open the Gem, give it this run's inputs from the usage prompt, and Gemini works through spend-approvals. The output - it normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status - can move straight into Sheets and Docs through the Workspace integration. You approve, adjust or discard first.

Setup, step by step

  1. Create a Gem in Gemini and name it after the job (for example: spend approvals).
  2. Make the Gem's instructions the contents of skill.md plus setup-prompt.txt.
  3. Run the setup conversation; the agent runs spend-approvals on fictional sample data first - approve that test before real work.
  4. Start each real run with that Gem and paste usage-prompt.txt with this run's inputs. Gems keep instructions between sessions, and Gemini's Workspace integration sits close to your Sheets and Docs.

Honest limits on Gemini

Gems are created and edited on the web, and some Workspace features depend on your plan. As with any assistant, approve the sample-data run before real data.

Questions people ask

Does the Spend Request Agent work on Gemini?

Yes - the agent is three plain-text files, and on Gemini they live in a Gemini Gem. The four setup steps below are the whole job: Create a Gem in Gemini and name it after the job (for example: spend approvals). Then make the gem's instructions the contents of skill.md plus setup-prompt.txt.

What does the Spend Request Agent produce on Gemini?

It normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status. Gemini can hand it straight to Sheets and Docs through the Workspace integration. Every run waits for your approval before anything is sent, spent, published or scheduled.

Is this affiliated with Gemini?

No. AI Agent Skills is an independent store. We are not affiliated with, endorsed by, or sponsored by Gemini or its makers. Platform names belong to their owners; capabilities change, so check Gemini's current documentation.

Run this agent on another assistant

Microsoft Copilot Hermes Instinct OpenClaw Muse Perplexity ChatGPT ChatGPT Dots Claude DeepSeek Town Grok

More finance teams agents on Gemini

Cash Flow Forecast Agent Budget Variance Agent Management Reporting Agent

AI Agent Skills is an independent store, not affiliated with Gemini or its makers. Platform names belong to their owners.