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

Spend approvals with the policy check done first - on ChatGPT

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

Get the Spend Request Agent - $19ChatGPT overview

What the Spend Request Agent does

If your week already starts in ChatGPT, this agent drops straight into that habit. 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 ChatGPT

Create a Project for the job, upload skill.md as a Project file and paste the setup prompt into the Project instructions. Run the setup once, approve the sample-data test, then start each run inside that Project so the rules stay loaded.

What a run looks like on ChatGPT

A run looks like this: you open the Project, paste the usage prompt with this run's inputs, and ChatGPT works through spend-approvals with the skill rules loaded. The output - it normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status - comes back as a draft you approve, adjust or discard; nothing is final until you say so.

Setup, step by step

  1. Create a Project in ChatGPT and name it after the job (for example: spend approvals).
  2. Upload skill.md as a Project file and paste setup-prompt.txt into the Project instructions.
  3. Start the setup conversation inside the Project; the agent runs spend-approvals on fictional sample data first - approve that test before real work.
  4. For each real run, open the same Project and paste usage-prompt.txt with this run's inputs. The rules stay loaded because they live in the Project.

Honest limits on ChatGPT

Projects and file uploads depend on your ChatGPT plan; check OpenAI's help center for current limits. Outside a Project, chat context resets and you re-paste the rules.

Questions people ask

Does the Spend Request Agent work on ChatGPT?

Yes - the agent is three plain-text files, and on ChatGPT they live in a ChatGPT Project. The four setup steps below are the whole job: Create a Project in ChatGPT and name it after the job (for example: spend approvals). Then upload skill.md as a project file and paste setup-prompt.txt into the project instructions.

What does the Spend Request Agent produce on ChatGPT?

It normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status. ChatGPT drafts it; you copy the approved version into the Google Sheet the setup created. Every run waits for your approval before anything is sent, spent, published or scheduled.

Is this affiliated with ChatGPT?

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

Run this agent on another assistant

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

More finance teams agents on ChatGPT

Cash Flow Forecast Agent Budget Variance Agent Management Reporting Agent

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