HomeLibraryServicesCase studiesAbout
consultance.ai
Book a discovery call →

Services

  • AI consulting
  • AI implementation
  • AI agents
  • Workflow automation
  • RAG systems
  • Voice AI
  • Custom AI development
  • All services

Library

  • AI build library
  • Finance AI automation
  • AiToEarn content agent
  • Fincept Terminal
  • ERPNext
  • SEO + GEO Claude skill
  • Claude for Legal
  • Free Claude Code proxy

Resources

  • Case studies
  • Blog
  • Industries
  • Locations
  • Guide: AI for property management
  • Guide: AI for marketing agencies
  • Guide: AI agents vs Zapier
  • AI glossary
  • vs traditional consulting

Company

  • About
  • Book a call
  • Contact
  • Privacy
  • Terms

© 2026 consultance.ai · AI, implemented.

audit → build → deploy

← Libraryconsultance.ai
Book a build call
Finance and data

Treasury Agent Stack

For CFOs and treasurers paying $75,000 to $1,000,000 a year for Kyriba or a PwC treasury engagement: 12 prompts covering cash position, payment review, forecast refresh, and covenant watch, running in your own Claude or GPT. No vendor lock, no TMS contract.

Have us build it — and hand you the keysor set it up yourself ↓
🔥 optional · live interactive tool

Open the TMS Cost Calculator

Browser-based. No signup. Drop in your numbers and see the trade in real time. Opens in a new tab so the prompts stay where you left them.

Launch the live tool ↗

Rent it forever, or own it once.

For CFOs and treasurers paying $75,000 to $1,000,000 a year for Kyriba or a PwC treasury engagement: 12 prompts covering cash position, payment review, forecast refresh, and covenant watch, running in your own Claude or GPT

Path A

Set it up yourself

The setup prompt and 0 task prompts are below — free. The cost is your time, and the risk of wiring it wrong on live data.

Jump to the prompts ↓
Path B

We wire it into your business

We would stand up the full treasury desk inside your own Claude or GPT account: the prompts wired to your data sources (banking portal exports, ERP module, credit agreement), the four core agents tuned to your entity structure and cash floor, the model-agnostic architecture set so the desk survives a vendor terms change, and the covenant watch calibrated to your actual credit agreement covenants. Done with you, then handed over so you own it. Your data runs in your tenant, never ours.

Book a build call →
Step 1

Paste this setup prompt — Claude installs it for you

Easy mode · paste this into Claude

Claude installs it for you, step by step.

Never used Claude before? It is free to start. Open it in a new tab, copy the prompt, paste it in. It asks one question, then walks you through everything.

  1. Step 1
    Open claude.ai ↗

    Sign up free. No card. Takes 30 seconds.

  2. Step 2

    One click. Lands on your clipboard.

  3. Step 3
    Paste + send

    Claude asks what you need + guides you the rest of the way.

Open claude.ai ↗
▸Tune the prompt for your level (optional)
▸Preview the prompt (you do not need to read it)
# Treasury Agent Stack — Guided Setup

Hello. I'm going to walk you through getting the Treasury Agent Stack running on your own data. Twelve prompts, four core treasury agents, no vendor dependency.

Before anything else, one question:

**Where do you run Claude today?**

(A) Claude.ai — browser or desktop app (the most common path, no coding needed)
(B) ChatGPT — same prompts work there too
(C) Claude Code in a Terminal — technical path, skip the browser steps
(D) Not sure yet

Reply A, B, C, or D and I'll take you from here.

---

## Branch A or B — claude.ai or ChatGPT (no coding, no Terminal)

Good. This is the right path for most users. No install. Takes about five minutes.

**Step 1 — Create a private Project**

In Claude: click "Projects" in the left sidebar, then "New project." Name it "Treasury Desk."

In ChatGPT: click "Explore GPTs" in the left sidebar, then "Create" or use Projects if your plan includes it.

This is your private workspace. Your bank exports, credit agreements, and cash position files stay in your own tenant. Nothing is shared with consultance.ai.

**Step 2 — Load your data**

You have three options. Pick the one that fits what you have today:

- **Paste it in.** Copy your bank balances, payment file, or cash position from your banking portal or ERP export and paste it directly into the chat. Every prompt reads pasted text. No upload needed.
- **Upload files.** In your Project, click "Add content" or the upload icon. Drop in bank statement exports (PDF or CSV), your ERP cash position report, or your credit agreement. Claude reads the files directly.
- **Use the Excel add-in (Claude for Microsoft 365 only).** If your firm has this, open Excel, highlight your cash position table or covenant schedule, and use the Claude side panel. The prompt reads the highlighted range directly. If the Claude icon is not in your Excel ribbon, your IT team may need to enable it. It is an add-in install, not a coding install.

Which one fits your setup? Tell me and I'll walk you through it step by step.

**Step 3 — Run Prompt 01 first**

Open the `treasury-agent-stack-prompt-vault.md` file from your bundle. Paste Prompt 01 into the chat and press Enter.

Prompt 01 sets up the advisory board and asks you two questions: what kind of entity are you (single, multi-entity, family office, PE-backed), and where your data lives. Answer both. Everything from Prompt 02 onward adapts to those answers.

This takes about two minutes.

**Step 4 — First-session drill: run Prompt 02 on a real cash position**

After Prompt 01 confirms your setup, paste Prompt 02 into the chat. Replace these tokens:
- `{{ENTITY_NAME}}` with your company name
- `{{PERIOD}}` with today's date
- `{{CASH_FLOOR}}` with the minimum cash balance your CFO considers safe

Then bring in your bank data the way you chose in Step 2.

Good output looks like this: a table of account balances, a projected end-of-day position, a working capital note, and a concentration flag if more than 40% of cash sits in one bank. If you see invented numbers with no source row, stop and check your data load.

**The review gate is not optional.** Every prompt has a review block at the bottom. A named person with authority must sign off before any output is acted on. Do not skip it.

**Step 5 — Run Prompts 03 through 05 in order**

These are the four agents the post promised: cash position (02), payment review (03), forecast refresh (04), and covenant watch (05). Run them in sequence for a full treasury cycle.

Prompts 06 through 12 are the over-delivery layer. FX exposure, liquidity stress, bank fees, investment policy, board report, counterparty risk, and the vendor-lock audit. Use them as your situation requires.

---

## Branch C — Claude Code / Terminal

If you are running Claude Code, the prompts work the same way. You can either:

- Paste them directly into a Claude Code session, or
- Load the `treasury-agent-stack-prompt-vault.md` as a file reference in your session context

No skill install is needed. These are XML prompts, not skills.

Run Prompt 01 first to set entity type and data source. Then run 02 through 05 in order.

For scheduled or headless runs: use a managed agent or script that loads the prompt file, injects your data source (a bank export file path, a pasted table, or a connector), and routes the output to a named reviewer before any action is taken.

---

## Common questions

**"Claude invented a number that isn't in my data."**
This means Prompt 01's data source was not confirmed before Prompt 02 ran. Go back to Prompt 01, re-run it, confirm the data source answer, then re-run Prompt 02. If it still invents, check that your uploaded file or pasted data is actually readable by Claude (ask it to repeat back three specific figures from the file before running the prompt).

**"The payment review agent flagged a payment I know is fine."**
That is the prompt doing its job. Every flag needs secondary approval from a named individual with payment authority. The agent does not know your business context; you do. Review the flag, document the override with a name and reason, and release. The flag log is your audit trail.

**"I don't have a credit agreement for the covenant watch."**
Prompt 05 needs the credit agreement to extract covenant definitions. If you don't have it loaded, paste the covenant table directly (covenant name, defined calculation, required level, testing date). The agent reads whatever you give it.

**"My firm has Bloomberg or LSEG connected to Claude for Financial Services."**
Before running the FX monitor (Prompt 06) or counterparty risk (Prompt 11), ask Claude to pull the relevant rates or credit ratings from the live connector first. Then run the prompt and the live data is already in context. If you're not sure whether the connector is active, ask your IT or Claude admin.

---

Ready when you are. Tell me where you got stuck and I'll walk you through it.

— consultance.ai

---

Related: [[anthropic-vs-openai-comp-vault]] · [[customer-zero-finance-ops]]

Free access

Unlock the complete library.

Enter your name and email to open every setup prompt and the full vault. No spam. No blasting. Always free.

One email when a new build ships. Unsubscribe anytime.

where it breaks

Before you connect live data

  • • Run dummy data first. Real client data is not a test bed.
  • • API keys never go in a public repo. Use env vars and a secrets manager.
  • • Add logging, access control, monitoring, and a rollback path before launch.
  • • Read the license. Forking a repo without checking is how lawsuits start.
license note

Credit the original author

Prompt set authored by consultance.ai. PwC and Kyriba are referenced as the standard and incumbent being replaced, no affiliation implied. The prompts run in your own Claude or GPT account and your data never leaves your tenant. They do the analysis; a named human with payment and signing authority owns every decision. Not treasury, legal, or financial advice.

the newsletter

AI news worth opening.

The AI tools, launches, and shifts that actually matter, in plain English. New library drops the moment they land.

100% freeNo paywall, everUnsubscribe anytime

Want this running in your business, not just your laptop? We build it and hand you the keys.

Book a build callBack to the library

Want this wired into your stack instead of running it yourself? That is our AI business consulting service.

More like this

Other builds worth a weekend

All repos →
Finance and data

Statement Matching and Reconciliation

For CFOs, controllers, and fund accountants: 10 prompts plus an offline extractor that match scanned bank, custodian, and brokerage statements to your ledger in seconds and return only the breaks, on your own machine. An alternative to BlackLine.

Setup guide →
Finance and data

Personal AI Trading Desk

For people who run their own book and pay 1% a year for a quarterly second opinion: 10 prompts that turn your own Claude into a bull, bear, and risk desk that argues before you trade, with a backtest guard. Paper and read only.

Setup guide →
Finance and data

Free Bloomberg Terminal Alternative

A free, open source terminal for analysts and finance founders. Track live stocks, bonds, and crypto, and run 37 AI agents, without paying for a Bloomberg seat.

Setup guide →
in one line

What is Treasury Agent Stack?

Treasury Agent Stack is a finance and data build in the consultance.ai AI Build Library. For CFOs and treasurers paying $75,000 to $1,000,000 a year for Kyriba or a PwC treasury engagement: 12 prompts covering cash position, payment review, forecast refresh, and covenant watch, running in your own Claude or GPT. No vendor lock, no TMS contract. It fits CFOs, corporate treasurers, assistant treasurers, and finance leaders at mid-to-large companies who want cash position, payment review, forecasting, and covenant monitoring done in their own Claude without a TMS contract or single-model dependency. Setup difficulty is Medium, with 4 plain-English steps.

What does Treasury Agent Stack do?

For CFOs and treasurers paying $75,000 to $1,000,000 a year for Kyriba or a PwC treasury engagement: 12 prompts covering cash position, payment review, forecast refresh, and covenant watch, running in your own Claude or GPT. No vendor lock, no TMS contract.

Who is Treasury Agent Stack for?

It fits CFOs, corporate treasurers, assistant treasurers, and finance leaders at mid-to-large companies who want cash position, payment review, forecasting, and covenant monitoring done in their own Claude without a TMS contract or single-model dependency.

How hard is Treasury Agent Stack to set up?

Medium to set up — 4 plain-English steps on the resource page.

How would consultance.ai build this out?

We would stand up the full treasury desk inside your own Claude or GPT account: the prompts wired to your data sources (banking portal exports, ERP module, credit agreement), the four core agents tuned to your entity structure and cash floor, the model-agnostic architecture set so the desk survives a vendor terms change, and the covenant watch calibrated to your actual credit agreement covenants. Done with you, then handed over so you own it. Your data runs in your tenant, never ours.

What are the licensing terms?

Prompt set authored by consultance.ai. PwC and Kyriba are referenced as the standard and incumbent being replaced, no affiliation implied. The prompts run in your own Claude or GPT account and your data never leaves your tenant. They do the analysis; a named human with payment and signing authority owns every decision. Not treasury, legal, or financial advice.

Want this built into your workflow?

Treasury Agent Stack is the starting point. On a free AI audit we map where it fits your stack and what consultance.ai would build around it.

Book your free AI audit