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

Spend Request Agent for Muse

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

Get the Spend Request Agent - $19Muse overview

What the Spend Request Agent does

Muse is built to take actions for you - this agent gives it a concrete job to own. 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 Muse

Give Muse the three files and ask it to keep skill.md as the standing rules for the job, then run the setup prompt and approve the fictional-data test before pointing it at real work. As with any action-taking agent, keep its approvals on.

What a run looks like on Muse

A run looks like this: you ask Muse to run spend-approvals with this run's inputs, and it works through the standing rules. The output - it normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status - is prepared with its approvals on, so you review before anything happens.

Setup, step by step

  1. Give skill.md, setup-prompt.txt and usage-prompt.txt to Muse and ask it to keep the skill as the standing rules for the job (for example: spend approvals).
  2. Run the setup prompt; the agent runs spend-approvals on fictional sample data first - approve that test before real work.
  3. Muse is built to take actions, not just answer - keep its approvals on, exactly the gates the agent is designed around.
  4. Trigger each real run with one message and this run's inputs.

Honest limits on Muse

Muse is brand new (September 2026) and its capabilities and rollout are changing week to week - check Meta's current documentation for what is available on your account.

Questions people ask

Does the Spend Request Agent work on Muse?

Yes - the agent is three plain-text files, and on Muse they live in Muse. The four setup steps below are the whole job: Give skill.md, setup-prompt.txt and usage-prompt.txt to Muse and ask it to keep the skill as the standing rules for the job (for example: spend approvals). Then run the setup prompt; the agent runs spend-approvals on fictional sample data first - approve that test before real work.

What does the Spend Request Agent produce on Muse?

It normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status. Muse prepares it with approvals on - you review before anything happens. Every run waits for your approval before anything is sent, spent, published or scheduled.

Is this affiliated with Muse?

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

Run this agent on another assistant

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

More finance teams agents on Muse

Cash Flow Forecast Agent Budget Variance Agent Management Reporting Agent

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