FREE COURSE · 13 MODULES

AI for Treasury Practitioners

A practical guide to understanding and using AI. No theory. No hype. Just what works.

Thirteen concepts a working AI product actually rests on — from how LLMs think to how to work effectively with Claude day to day, told through one running example: TOSY, a real treasury AI agent in production.

After this course, you will be able to
  • ✓ Explain what LLMs are actually good and bad at — and why that matters for your job
  • ✓ Write clear prompts and system prompts using a repeatable structure
  • ✓ Tell agents, agent orchestration, MCP, and RAG apart — and know when each applies
  • ✓ Explain why evals and caching matter, even if you didn't build them yourself
  • ✓ Work more effectively with Claude and Claude Code, day to day

Alina Turungiu · TreasuryOS · treasuryease.com

How LLMs Actually Work

Treasury analogy

The Treasury Analogy

Imagine a new hire who has read every treasury textbook, every bank statement format, every regulation. They can predict what comes next in a sentence because they've seen millions of similar patterns. But they have no real experience. They haven't made a payment. They haven't reconciled an account. They pattern-match brilliantly but don't truly "understand."

What It Means For You

LLM = Large Language Model. Trained on text to predict the next word.

They are extremely good at:

  • • Summarizing, writing, analyzing
  • • Following complex instructions
  • • Generating code and structured output

They are bad at: math, real-time data, remembering past conversations, being 100% accurate.

Your job: give clear instructions and verify the output. AI does the heavy lifting. You do the thinking.

Prompt Engineering

How you talk to AI determines what you get back

Vague prompt (bad)

"Give me a bank extract."

Result: AI guesses format, currency, date range. Output is generic and wrong.

Clear prompt (good)

"Generate a sample MT940 for account RO49AAAA, Oct 2025, 15 transactions, RON, with salary payments."

Result: Exactly what you need.

The 4 Elements of a Good Prompt
Role

Who are you talking to?

"You are a treasury systems expert."

Context

What do you already know?

"We use Coupa and SAP."

Task

What do you want?

"Build a cash position dashboard."

Format

How do you want it?

"Return JSON with currencies."

System Prompts

The job description for your AI agent

Treasury analogy: When a new employee joins your team, you give them a document: who we are, what we do, how we communicate, what we never do. They refer to it for every decision.

A system prompt is exactly that. Instructions the AI receives before any conversation starts. The user never sees them. But they determine everything about how the AI behaves.

This is the most important part of any AI product. A mediocre system prompt = a mediocre AI assistant, regardless of how smart the model is.

What goes inside a system prompt:
Identity

Who the AI is, its expertise

Rules

What it must and must not do

Knowledge

Domain-specific context

Format

How to structure responses

Guardrails

Safety and boundaries

AI Agents

AI that doesn't just answer, it acts

Regular Chatbot

You ask: "What's my cash position?"

AI says: "I don't have access to your data."

It can only talk. It cannot do.

AI Agent

You ask: "What's my cash position?"

AI queries your database, pulls balances, converts currencies, and returns the answer.

It thinks, decides which tools to use, and acts.

How an AI Agent works:
1. Receive

User asks a question

2. Think

Decide what tools to use

3. Act

Query database, call API, calculate

4. Respond

Return structured answer

Agent Orchestration

Multiple specialized agents working together

Treasury analogy: You don't have one person doing everything. Cash manager handles cash. FX dealer handles FX. Risk manager handles risk. A Head of Treasury routes work to the right person. Agent orchestration is the same: specialized AI agents coordinated by a router.

Router

Decides which agent handles the request

CashAgent

Cash position, balances, statements

FXAgent

FX rates, exposure, conversions

ReportAgent

Dashboards, forecasts, exports

You already built this in TOSY.

MCP (Model Context Protocol)

SWIFT for AI: a standard way for AI to connect to tools

Treasury analogy: SWIFT is a universal protocol for banks to communicate. MCP is a universal protocol for AI to communicate with tools and data sources. Instead of building custom integrations for each tool, MCP provides one standard. Created by Anthropic (the company behind Claude).

What MCP enables:
Read files — AI reads documents, spreadsheets, PDFs from your system
Query databases — AI pulls data directly from Supabase, PostgreSQL, etc.
Call APIs — AI connects to external services (banks, ERPs, tools)
Take actions — In Claude.ai: MCP connects Claude to Google Drive, Gmail, Notion, Slack, and more. AI creates records, sends notifications, updates data.

In your product: MCP lets TOSY connect to your users' data sources.

RAG (Retrieval Augmented Generation)

AI that looks things up before answering

Treasury analogy: When a colleague asks you about a bank agreement, you don't answer from memory. You go to the folder, find the document, read the relevant section, and then answer. RAG is exactly this for AI.

How RAG works:
1 · User asks

"What are my bank fees for Q3?"

2 · Search

AI searches your documents and data

3 · Retrieve

Finds the relevant sections/records

4 · Generate

Answers based on actual data, not guessing

Why it matters: Without RAG, AI makes things up ("hallucinations"). With RAG, AI answers from your actual data.

Game changer for TOSY: imagine users asking "What does my credit agreement with Bank X say about covenants?" and getting an accurate answer.

Evaluation (Evals)

How you know if your AI is actually working

Treasury analogy: Treasury reconciliation. You compare what should be there with what is there. Evals do the same for AI: compare AI's answers with correct answers. Like a treasury audit, but for your AI.

Without Evals

"It seems to work."

"A user complained it gave wrong FX rate."

"I think the last update made it worse but I'm not sure."

You are flying blind.

With Evals

"TOSY answers 94% of cash queries correctly."

"FX conversion accuracy dropped 3% after last update."

"Reconciliation agent hallucinates on 6% of edge cases."

You have numbers. You can improve.

Start simple: 50 questions you know the answer to. Run them through TOSY. Count how many it gets right.

Caching

Pay once, use many times

Treasury analogy: Instead of calling the bank every time someone asks for the balance, you check once in the morning and use that number all day. Caching stores repeated AI instructions so you pay once, not every time.

Why it matters for TreasuryOS:

TOSY has a system prompt (~4,000 words).

60 users × 10 messages/day = 600 API calls/day.

Without cache: you send 4,000 words × 600 times. You pay for all of it.

With cache: you send 4,000 words once. The next 599 calls cost a fraction.

Prompt caching can reduce API costs by up to 90%.

You already implemented this. Now you know why it matters.

Claude Code

Your AI development partner in the terminal

Claude Code is a command-line tool where AI reads your entire codebase, understands context, writes code, runs tests, and fixes bugs. It's not a chatbot. It's a co-developer who sees everything.

How to get the best results:
Be specific — "Fix the FX conversion bug in CashPosition component where EUR to RON uses wrong rate" beats "fix the bug."
Give context — "We use Next.js 14, Supabase, TypeScript. The component is in /components/cash/. It should match the pattern in FXDashboard.tsx."
One task at a time — Don't ask it to build a feature, fix 3 bugs, and refactor. Split into separate requests. Each one clear and focused.
Verify output — Always review the code. Run tests. Check edge cases. AI writes fast but doesn't always write correct.
Use CLAUDE.md — A file at the root of your project that gives Claude Code persistent context about your codebase, architecture, and rules.

Connectors & Skills

Extending what Claude can do in claude.ai

Connectors (MCP in practice)

In Claude.ai settings, you can connect external services:

  • • Google Drive
  • • Gmail
  • • Google Calendar
  • • Notion
  • • Slack, Jira, and more via Zapier

Once connected, Claude can read your Drive files, search emails, create calendar events, etc. These are MCP servers running behind the scenes.

Skills (in Claude Code)

Skills are instruction sets that teach Claude Code how to do specific tasks well:

  • • Create Word documents (.docx)
  • • Create presentations (.pptx)
  • • Create spreadsheets (.xlsx)
  • • Create PDFs
  • • Frontend design, and more

Think of skills as best-practice recipes. Claude Code reads them before starting a task to ensure quality output.

Both are examples of giving AI access to tools and knowledge it doesn't have by default.

Working Effectively with Claude

Practical rules for getting better results every day

01
Start with what you want, not how to get there

"I need a 13-week cash forecast" is better than explaining the steps.

02
Give examples of good output

Show Claude what the result should look like. A screenshot, a sample, a format.

03
Challenge the output

Ask: "Are you sure? What could be wrong here? Attack this." Claude gets better when pushed.

04
Use Claude AI for strategy, Claude Code for building

Think with Claude AI. Build with Claude Code. Don't mix the two.

05
Break complex tasks into steps

Don't ask for everything at once. Phase 1, Phase 2, Phase 3. Verify each before moving on.

06
Save your best prompts

When something works perfectly, save the prompt. You'll need it again.

07
Don't accept the first answer

Claude's second or third attempt is often better. Iterate. Refine. Push back.

Your AI Stack

What you already built (and didn't know it had a name)

✓Prompt EngineeringYou do this every day with Claude
✓System PromptsTOSY has specialized system prompts
✓AI AgentsTOSY is an AI agent with tools
✓Agent OrchestrationCashAgent, FXAgent, Router
✓MCP / Tool UseImplemented through AI tools
✓CachingPrompt caching for API cost reduction
○RAGNext phase: document search for users
○EvalsNext phase: systematic testing for TOSY

6 out of 8 core AI concepts: already in production.

You don't need to learn AI theory.
You need to label what you already do.

"I don't teach AI theory.

I build AI systems in production.

Then I explain what I built."

Alina Turungiu | TreasuryOS

✓ Course complete

Key takeaways

LLMs pattern-match brilliantly but don't truly understand. Give clear instructions, verify the output.

A good prompt has 4 elements: Role, Context, Task, Format. A system prompt is the same idea, set once.

Agents act, not just answer. Orchestration routes work between specialized agents, the way a Head of Treasury routes work between people.

MCP connects AI to tools like SWIFT connects banks. RAG grounds answers in your real data instead of guesses.

Evals tell you if your AI actually works. Caching makes running it affordable. You probably need both, eventually.

You don't need to learn AI theory. You need to label what you already do.

Alina Turungiu · TreasuryOS · treasuryease.com