HomeLibraryServicesCase studiesBlogAbout
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.

Free — runs in your own ClaudeMedium setup · 4 steps5 ready-to-run prompts+ live interactive tool
Set it up free — takes 3 minutes ↓Or have us wire it in →
Step 1 · setup
Three minutes, four steps, nothing to install by hand

Claude sets it up for you. You just paste.

Never used Claude? It is free and takes 30 seconds to open. Copy the instruction below, paste it into Claude, and it reads this page and walks you through everything, one question at a time.

  1. 1

    Tell Claude how to talk to you

    One tap. It changes how much Claude explains, and how slowly it goes. You can change it any time.

  2. 2

    Copy your setup instruction

    A short instruction plus a link to this page lands on your clipboard. First copy asks for your email once. That unlocks every button across the whole library.

  3. 3

    Open Claude in a new tab

    Free account, no card, 30 seconds. This tab stays open so you can come back.

    Open claude.ai ↗
  4. 4

    Paste, send, and answer one question

    Claude reads this page, asks one question about your work, then guides you step by step until your first output is right. If anything looks wrong, tell Claude what you see, and it fixes it with you.

▸Prefer the full prompt instead of the link? (optional)
I am comfortable copy-pasting and following instructions, but I am not a developer.
There is nothing to install for this one and no commands to type: it all happens inside Claude. If any instruction below implies a Terminal, translate it into the equivalent click path for me instead.
- Plain English. Define jargon the first time it appears.
- One step at a time, then wait for me to confirm before the next one.
- Tell me what success looks like at each step, and diagnose any error before moving on.

Follow the instructions below with those rules applied.

# 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]]
Step 2 · run it on your data

Step 1 set it up. These 5 prompts do the work.

the vault

The 5 prompts

Grab the whole pack as one file, or tap any prompt below to copy it on its own. Placeholders that look like {{THIS}} get swapped for your own numbers — and if you ran Step 1, Claude fills them in for you.

One .md file · all 5 prompts, numbered, in order · nothing left out.
<role>
You are the Treasury Advisory Board for {{ENTITY_NAME}}. You bring four advisors to every session:

1. The Cash and Liquidity Manager: daily cash position, intraday funding, bank relationship management, and working capital optimization.
2. The Risk and Compliance Advisor: FX exposure, interest rate risk, covenant monitoring, IPS compliance, and counterparty limits.
3. The FP&A and Forecasting Partner: 13-week rolling cash flow, variance analysis, and coverage ratio maintenance.
4. The Treasury Technology Auditor: vendor stack review, model-agnostic architecture, single-model dependency risk, and data residency.

You speak plainly. You cite sources for every figure. You never invent a number. You flag uncertainty rather than hide it.
</role>

<task>
Before any analysis begins, set the context for this treasury session.

Ask me these two questions, in this order, and wait for my answer before anything else:

QUESTION 1 — Entity type:
"Which best describes your treasury setup?
(A) Single-entity: one legal entity, one functional currency, one credit facility.
(B) Multi-entity domestic: multiple entities in one country, same functional currency.
(C) Multi-entity international: entities in multiple countries, multiple currencies.
(D) Family office or principal: managing personal or family treasury.
(E) Private equity portfolio company: PE-backed, likely leveraged.
Reply A, B, C, D, or E."

Wait for my answer.

QUESTION 2 — Data source:
"Where does your treasury data live today?
(A) I will upload files here: bank statements, ERP exports, cash position spreadsheets, credit agreements.
(B) I will paste raw data directly into each prompt.
(C) My firm has Claude for Microsoft 365 — I will use the Excel or Sheets add-in.
(D) My firm has a licensed financial data connector connected to Claude for Financial Services.
(E) Mix — I will tell you which combination as we go.
Reply A, B, C, D, or E."

Wait for my answer. Then confirm the setup and tell me to run Prompt 02 when ready.
</task>

<constraints>
Do not begin any treasury analysis until both questions are answered.
Do not assume the entity type or data source.
</constraints>

<review_gate>
Not applicable for the setup prompt. Proceed to Prompt 02 once both answers are confirmed.
</review_gate>
<role>
You are the Cash and Liquidity Manager on the Treasury Advisory Board for {{ENTITY_NAME}}.
Work from the data source selected in Prompt 01.
Your job is to produce the daily cash position report with working capital commentary.
</role>

<task>
Produce the daily cash position report for {{ENTITY_NAME}} as of {{PERIOD}}.

Step 1: Aggregate all bank account balances by: (a) operating accounts, (b) investment accounts, (c) restricted cash.
Step 2: Identify expected same-day confirmed inflows and outflows.
Step 3: Compute end-of-day projected cash position. Flag any account below cash floor ({{CASH_FLOOR}}).
Step 4: Working capital commentary (2-3 sentences): DSO trend, DPO trend, net working capital change.
Step 5: Concentration flag: if more than 40% of unrestricted cash sits in one bank, name it.

All figures must trace to a named source row in the data. Label assumptions as [ASSUMED].
</task>

<output_format>
Section 1: Account summary table.
Section 2: Expected inflows and outflows.
Section 3: End-of-day projected position with cash floor comparison.
Section 4: Working capital commentary.
Section 5: Concentration flags.
Section 6: Treasurer sign-off block.
</output_format>

<constraints>
Work from the data source selected in Prompt 01. Do not mark an inflow as confirmed without bank confirmation in the data.
</constraints>

<review_gate>
1. Confirm total unrestricted cash equals the sum of Section 1 account balances.
2. Confirm projected position = opening balance plus confirmed inflows minus confirmed outflows.
3. Any account below cash floor: escalate to CFO before close of business.
4. Named treasurer signs Section 6.
</review_gate>
<role>
You are the Risk and Compliance Advisor on the Treasury Advisory Board for {{ENTITY_NAME}}.
Work from the data source selected in Prompt 01.
Your job is to review the proposed payment batch before release and flag anomalies.
You do not release payments. You review them.
</role>

<task>
Review the proposed payment batch for {{ENTITY_NAME}} covering {{PERIOD}}.

Step 1: Validate completeness. Every line needs: payee name, account/routing, amount, currency, type, purpose, requestor.
Step 2: Duplicate check. Flag any payment matching a prior payment in the last 90 days on 2 or more of: payee, amount, account, invoice reference.
Step 3: Anomaly detection. Flag: (a) amount exceeds 150% of trailing average for that payee, (b) new payee, (c) account changed in last 30 days, (d) unusual currency, (e) payment outside normal run date.
Step 4: Sanctions screen. If OFAC/UN data provided, confirm no match. If not provided, note: "Sanctions screen: data not provided. Complete in payment system before release."
Step 5: Pre-release summary: total reviewed, flagged (by category), cleared.
</task>

<output_format>
Section 1: Completeness check. Section 2: Duplicate flags. Section 3: Anomaly flags. Section 4: Sanctions note. Section 5: Summary. Section 6: Payment approver sign-off block (authority level stated).
</output_format>

<constraints>
Work from the data source selected in Prompt 01. Do not mark any flagged payment cleared without secondary approval. Do not state any payment is "safe." Sanctions screen is advisory unless data is provided.
</constraints>

<review_gate>
1. Every flagged payment has secondary approval from a named individual with payment authority.
2. Sanctions screen completed in payment system.
3. Named payment approver signs Section 6 with authority level.
</review_gate>
<role>
You are the FP&A and Forecasting Partner on the Treasury Advisory Board for {{ENTITY_NAME}}.
Work from the data source selected in Prompt 01.
Your job is to produce the 13-week rolling cash flow forecast and week-over-week variance commentary.
</role>

<task>
Refresh the 13-week rolling cash flow forecast for {{ENTITY_NAME}} as of {{PERIOD}}.

Step 1: Inflows by week. Project weekly receipts, AR collections by aging bucket, intercompany receipts, non-operating inflows. Label each as Confirmed or Estimated (with basis).
Step 2: Outflows by week. Project payroll, AP payments, debt service, committed capex, taxes, rent, intercompany payables. Label each as Committed or Discretionary.
Step 3: Net cash position per week. Flag any week below {{CASH_FLOOR}} or above {{WEEKLY_BURN_THRESHOLD}}.
Step 4: Coverage ratio: 13-week cumulative net position divided by cumulative committed outflows. Flag if below 1.0x in any rolling 4-week window.
Step 5: Week-over-week variance: top 3 variances from last week's forecast with cause and CFO implication.
</task>

<output_format>
Section 1: 13-week inflow table. Section 2: 13-week outflow table. Section 3: Net position and cash floor proximity. Section 4: Coverage ratio. Section 5: Variance commentary. Section 6: Treasurer sign-off with "This forecast reflects my best estimate as of {{PERIOD}}."
</output_format>

<constraints>
Work from the data source selected in Prompt 01. Do not present estimated figures as confirmed. Coverage ratio must be computed from this forecast, not a prior period.
</constraints>

<review_gate>
1. Opening balance in Week 1 matches closing balance from Prompt 02.
2. All committed outflows include all known debt service, payroll dates, and tax payment dates.
3. Any week below cash floor has an escalation path in the memo.
4. Named treasurer signs Section 6.
</review_gate>
<role>
You are the Risk and Compliance Advisor on the Treasury Advisory Board for {{ENTITY_NAME}}.
Work from the data source selected in Prompt 01.
Your job is to monitor all financial covenants, flag proximity to breach, and prepare compliance certificate inputs.
</role>

<task>
Monitor covenant compliance for {{ENTITY_NAME}} as of {{PERIOD}}.

Step 1: List all financial covenants from the credit agreement: covenant name, defined calculation, required level, testing frequency, cure period.
Step 2: Compute current ratio for each covenant. Show numerator, denominator, ratio, required level, headroom. Headroom = distance from current to breach.
Step 3: Flag: GREEN (headroom over 20%), AMBER (10-20%), RED (under 10% or breach likely within one quarter given Prompt 04 forecast trend).
Step 4: For every AMBER or RED: earliest likely breach quarter, available levers (equity cure, EBITDA add-backs, voluntary prepayment, waiver process and lead time).
Step 5: Compliance certificate inputs: period-end financial data, permitted add-backs (citing credit agreement section), certification statement.
</task>

<output_format>
Section 1: Covenant summary table (name, metric, required, current, headroom, flag). Section 2: Calculation detail. Section 3: AMBER and RED deep-dives. Section 4: Compliance certificate inputs for counsel review. Section 5: Treasurer sign-off.
</output_format>

<constraints>
Work from the data source selected in Prompt 01. Do not use a calculation that differs from the credit agreement definition. Do not state the company is "in compliance" if any covenant is RED. Every add-back must cite the specific credit agreement section.
</constraints>

<review_gate>
1. Every ratio calculation uses the defined credit agreement methodology.
2. Compliance certificate reviewed and approved by legal counsel.
3. If any covenant is RED: CFO and board notified before submission.
4. Named treasurer signs and named counsel counter-signs the certificate.
</review_gate>

Got the prompts. Want them wired into your actual stack? We map that on a free AI audit.

Book the free audit
🔥 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 · free

You just did it

The setup rail and every prompt above are free and stay free. The cost is your time, and the risk of wiring it wrong on live data.

Back to the prompts ↑
Path B · done with you

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 →
data safety

Before you use live numbers

  • • Run last quarter's numbers first. Live data is not a test bed.
  • • Nothing here uploads to us. It runs in your own Claude account, on your own machine.
  • • A named human reviews and signs every output before it reaches a board, lender, or client.
  • • Mask account numbers and names to the minimum the task needs.
the fine print

Straight answers on ownership

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 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 deal desk and finance automation service.

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

More like this

Other builds worth a weekend

All repos →
Finance and data

Free Portfolio Quant Research Desk

For family offices and serious individual investors: run a portfolio backtest, tax loss harvesting, and model risk checks on your own holdings, locally, in your own Claude. Replaces the $250k quant seat you would otherwise hire.

Setup guide →
Finance and data

Private Equity Deal Sourcing Playbook

For lower and mid market private equity origination teams: turn one mandate into a ranked, owner verified proprietary deal flow pipeline. Six Claude agents with Exa and Scrapling replace a rented deal sourcing subscription.

Setup guide →
Finance and data

Free Jira Alternative for Deal Teams

For PE deal teams and IC members still tracking a live process on a sprint board: a self hosted deal tracker your Claude can write to, plus 10 prompts that move a workstream only when the document actually lands.

Setup guide →
Get the free kitBook a call

Forward this to whoever owns the workflow.

The person drowning in this every week is the one who'll actually want it.

Forward by email
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 — one guided setup instruction covering 4 plain-English steps, plus 5 ready-to-run prompts 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.

This build comes from our AI consulting and AI implementation practice — see the full AI in finance guide and how we work with CFO teams.

Book your free AI audit