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

Spend approvals with the policy check done first - on Grok

The $19 Spend Request Agent runs on Grok as three plain-text files: set it up once in a Grok Skill or Bot, approve a sample-data test, then trigger each run with the usage prompt and this run's inputs.

Get the Spend Request Agent - $19Grok overview

What the Spend Request Agent does

If you work inside X or Grok's apps, this agent becomes a standing Skill there. 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.

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.

Where the three files go in Grok

Attach the three files to a chat or build a Grok Skill/Bot with skill.md as the standing expertise, then run the setup prompt and approve the fictional-data test. Skills keep the rules persistent between asks.

What a run looks like on Grok

A run looks like this: you invoke the Skill with this run's inputs, and Grok 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 - comes back for your review, and with Grok's Office document generation it can arrive as a formatted file.

Setup, step by step

  1. Create a Grok Skill (or custom Bot) and name it after the job (for example: spend approvals).
  2. Load skill.md as the standing expertise and setup-prompt.txt as the setup instructions.
  3. Run the setup; the agent runs spend-approvals on fictional sample data first - approve that test before real work.
  4. For each real run, ask with usage-prompt.txt and this run's inputs. Skills keep the rules persistent between asks.

Honest limits on Grok

Grok's features differ between X, the standalone apps and the API, and some sit behind paid tiers - check xAI's current docs for what your plan includes.

Questions people ask

Does the Spend Request Agent work on Grok?

Yes - the agent is three plain-text files, and on Grok they live in a Grok Skill or Bot. The four setup steps below are the whole job: Create a Grok Skill (or custom Bot) and name it after the job (for example: spend approvals). Then load skill.md as the standing expertise and setup-prompt.txt as the setup instructions.

What does the Spend Request Agent produce on Grok?

It normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status. Grok can return it as a generated Office document or plain text you paste into your Sheet. Every run waits for your approval before anything is sent, spent, published or scheduled.

Is this affiliated with Grok?

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

Run this agent on another assistant

Instinct Claude Gemini Hermes OpenClaw ChatGPT DeepSeek Perplexity Microsoft Copilot Town Muse

More finance teams agents on Grok

Cash Flow Forecast Agent Budget Variance Agent Management Reporting Agent

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