AI-assisted drafting, editing, outlining, and summarizing of finance documents, presentations, emails, and communications

Here's the full Claude system I use for finance work.

(Everything a finance team needs to stop wasting hours on manual work)

👉 Comment "Claude" and I'll send you the full set.

I'm limiting this to the first 1,000 comments.

Businesses bring me in to run finance workshops and show their teams how to actually use AI for real finance work.

Most teams I train are using maybe 5% of what Claude can do.

They watch a few tutorials. They paste in random prompts. They get mediocre results and conclude it's overhyped.

No one ever gave them a structured way to use it for the actual job: the reporting, the analysis, the board pack.

So I packaged my best resources into one set: The Claude Finance Toolkit.

Inside, you'll find:

1. The Free Claude Course for Finance
2. Top 50 Claude Tips
3. Top 50 Claude Shortcuts
4. The Claude Finance Playbook
5. Claude for Board Packs & Presentations Guide

Practical guides, prompts, and workflows to save time, sharpen your numbers, and make better decisions.

I've watched owners burn an entire weekend on a board deck that Claude could draft in 30 minutes.

This is the shortcut I wish every finance team had on day one.

👉 Comment "Claude" and I'll send you the full set.

♻️ Repost to help a finance colleague still doing it the hard way.

AI is transforming finance, and I use it every day.

But here’s the mistake I see companies starting to make…

They’re trusting AI to produce financial analysis, forecasts, board reports, and even strategic recommendations without an experienced finance professional validating the output.

That’s a costly gamble.

AI is incredibly good at organizing information, identifying patterns, and accelerating analysis. What it doesn’t do is exercise professional judgment.

It doesn’t know:
• when source data is incomplete
• whether assumptions are reasonable
• if revenue recognition is being interpreted correctly
• whether a margin trend is actually meaningful or simply a timing issue
• when one bad formula can change an entire forecast

The most dangerous AI errors aren’t obvious. They look polished. They sound confident. And they can quietly make their way into executive decisions.

One incorrect assumption in a cash flow forecast can affect hiring.
One inaccurate margin analysis can change pricing.
One flawed financial model can influence an acquisition or investment decision.

The cost isn’t the AI.
The cost is believing it can’t be wrong.

The future of finance isn’t AI replacing finance professionals.

It’s AI making experienced finance and accounting professionals exponentially more effective.

Speed is valuable.

Accuracy is priceless.

I spent months telling my finance team to use AI more.

Then I sat down and saw the problem.

It was the prompts.

Vague inputs get vague outputs. And vague outputs don't help a CFO make better decisions.

Here are the prompts I keep coming back to:

**1. Variance analysis**
"Here is our budget vs actuals [paste]. Identify the top 5 variances, explain likely causes, and suggest 3 questions I should be asking my team."

**2. Board narrative**
"Summarize this financial data [paste] for a board audience. Lead with the headline. Keep it under 200 words. No jargon."

**3. Scenario planning**
"You are a CFO. Given these assumptions [paste], build 3 scenarios: base, upside, downside. Flag the top 2 risks in each."

**4. Headcount review**
"Review this headcount plan [paste]. Identify gaps, redundancies, and flag any roles worth reconsidering before the next budget cycle."

**5. Executive storytelling**
"Turn this data into a narrative for a non-finance audience. Explain why we missed or beat plan and what it means for the next quarter."

The secret is treating AI like a brilliant analyst who needs full context and a clear ask.

Give it both, and the output changes completely.

**What AI prompts are actually working in your finance workflow?**

AI has changed how I work.

Faster reconciliations. Smarter tax analysis. Automated reporting.

But accounting is one of the most sensitive professions when it comes to data. Client financials, tax returns, payroll records, bank statements — one breach can destroy trust forever.

So before I ever touched an AI tool for client work, I built a strict data security framework. Here it is:

1. Remove all identifying information first
Before inputting any financial data into AI, I replace client names, business names, TINs, and account numbers with placeholders. The AI sees "Client A" and "Account XXXX" — never the real details.

2. Never upload raw financial documents
Bank statements, balance sheets, and tax returns stay in my secure system. I extract only the figures I need and input those manually. No full document ever goes into a public AI tool.

3. Use AI only for the thinking — not the data storage
I use AI to analyse patterns, draft explanations, or check calculations — not as a database. The actual client data lives in encrypted, compliance-approved software only.

4. Choose enterprise AI tools with clear data agreements
I only use AI platforms that guarantee: no training on my inputs, data encryption in transit, and compliance with data protection regulations. Anything less is a risk I won't take.

5. Separate AI tools by sensitivity level
General writing tasks (emails, reports, templates) → standard AI tools.
Anything touching client numbers → private or locally hosted AI only.
This boundary keeps sensitive work in a controlled environment.

6. Inform clients and document the process
Whenever AI assists with client work, I note it. I'm transparent with clients about what tools support my process and how their data is protected. In accounting, trust is everything.

AI doesn't replace professional judgment — it sharpens it.

But only if you handle data with the same integrity your clients expect from you.

Are you using AI in your accounting or finance work? I'd love to hear how you're managing data security. Drop it in the comments 👇

♻️ Repost to help fellow accountants work smarter and safer.

#Accounting #AI #DataPrivacy #ClientConfidentiality #FinanceTech #AIinAccounting #CPA #DataSecurity #ProfessionalDevelopment #TaxProfessional

2 years ago, I was scared of AI.

Now I use Claude almost every day in my finance job.

I’m not a tech person. When AI first showed up at work, it felt confusing and overwhelming. And hearing “AI will replace jobs” didn’t help. So I stayed away.

But about 10 months ago, I challenged myself:
👉 What if I just try to learn it?

Not just asking ChatGPT simple questions, but digging deeper and seeing how AI tools can help me save time and do my job better.

At first, there was a lot of trial and error. Some prompts didn’t work. Some outputs didn’t make sense. But slowly, things started to click. Here’s what I’ve learned:

1️⃣ Make the AI prompts as specific as you can.
Being specific minimizes bandwidth and optimizes output.

2️⃣ Think outside the box. Be open to try.
I’ve used it to write, research, extract, analyze, automate, etc.

3️⃣ Understand limitations through testing.
Identify areas of limitation where you need to use judgment.

To me, AI feels a lot like computers decades ago.

Yes, it eliminated jobs. But it also created new ones. And the people who learned how to use computers had the biggest advantage.

AI is the same. Keep an open mind. Try new things. Learn a little every day. Make AI work for you, not against you.

I look forward to continuous learning this year. Curious — how are you using AI in finance today?

I've been using AI heavily in finance for a year. Here's what I've found actually matters:

1️⃣ If your accounting system doesn't connect easily with an external AI (ChatGPT, Claude, etc.), you're using the wrong accounting system. Built-in AI tools in accounting systems like QBO are rarely as capable as the real thing.

2️⃣ Know the privacy risks. My rule: strip out identifying information before uploading any document.

3️⃣ Treat it like a new staff accountant. You have to check its work. You have to train it. It will make mistakes.

4️⃣ Direct connectors to Google Drive or cloud storage are hit or miss. If accuracy matters, export the reports and upload manually to the AI model.

5️⃣ Before you review anything, ask it to double-check its own work first. It catches its own errors more often than you'd think.

6️⃣ Reconciliations and matching tasks are where it shines. Add agents into the mix, and you're automating a significant chunk of staff-level accounting work.

7️⃣ The future belongs to finance professionals who understand how these models think, know roughly what the answer should look like, and can verify the math. Your experience-based gut instinct matters more now, not less.

8️⃣ Cash flow forecasting is where I'd start for most businesses. It's the single highest-impact use case I've found.

9️⃣ For FP&A work specifically, Claude is the clear winner — and worth the paid upgrade.

🔟 Information overload is real. My fix: ask it to cut the output by 50%, then ask it to simplify further. Forces it to distill down to what actually matters.

AI won't replace experienced finance professionals. But it will replace those who don't know how to use it.

#Finance #AI #Accounting #FPandA #CFO

LinkedIn thread is filled with posts on how CFOs are using AI for driving business strategy. When in reality AI cannot even give a proper social media content strategy.

AI can sound like it is offering deep wisdom when you ask it frame a strategy. But will it really work? There is no guarantee. At the end of the day it is a language engine. It knows how to sound smart without being really smart.

Human beings also often imitate and may copy others in decisions. But we get a sudden spark out of nowhere when shampoo runs into our eyes or while waiting at the traffic signal, which makes us go back to the drawing board to revise the strategy.

I doubt AI will ever do that.

So, dear CFOs, if you are being anxious that you are falling behind others in using AI to drive your financial strategy, don't be. Those posts are FOMO baits from those who have no clue how finance, forecasting, or strategy works.

I use AI as a nice research assistant, as a brain storming partner, as an editor, and as a clerk. I may one day even let it handle my spreadsheets for real. But I am not ever going to use it as my advisor.

PS: The few times I used AI's "advise" to increase the engagement potential of my post, they bombed miserably. That is how bad it is as an advisor.

I wrote about AI slop back in December.

Marketing emails that sound like robots.
LinkedIn posts that all say nothing.
AI buttons on every app that make everything worse.

It's gotten worse. Way worse.

It jumped departments.

I'm seeing it in spreadsheets now.
Excel models with 20 tabs and yellow input cells on every single one.

Formulas that reference tabs that reference other tabs. Nobody can trace the logic. Nobody checks if it even makes sense.

It looks professional. That's the problem.

Presentations too. Every deck has the same gradient sidebar.

Metrics cards that never end. Total Revenue. Revenue Growth. Revenue Growth Rate. Revenue Growth Rate vs. Prior Quarter. Four cards saying the same thing in different colors. Accent bars across the top like we're designing a magazine.

And a "Key Takeaways" slide that takes away absolutely nothing.

Then the writing. Em dashes everywhere. "The quarterly results were strong — driven by operational efficiency — and positioned the company for growth." That's not a sentence. That's AI doing jazz hands.

Here's what actually happened. People used to be bad at Excel. They knew they were bad at Excel. So they kept it simple. One tab. One purpose. You could follow the logic.

Now AI builds a 20-tab model in 30 seconds and nobody asks if tab 14 needs to exist.

I use AI every day. I run finance, marketing, tech, and HR with it. I build dashboards, automate workflows, draft reports. I'm not some guy yelling at the cloud.

But "AI can build it fast" doesn't mean it should exist.

The whole point was to enhance what we do. Not bring the average down. Not flood every shared drive with pretty garbage nobody reads past tab 3.

More stuff is not better stuff.

Stop it. Think. Then build.

What's the worst AI slop you've seen at work?

Workflow I teach how to turn raw financial data into a clean, executive-ready presentation in minutes using AI.

✲ Step 1 — Upload Your Financial Data

Start with your core files:

- P&L
- balance sheet
- cash-flow statement
- KPI reports
- variance analysis

Upload them into ChatGPT (or Copilot).

✲ Step 2 — Generate the Key Insights

Use this prompt:

"You are a CFO-level finance analyst. Analyze the uploaded data and extract the most important insights for an executive presentation.

Focus on:

key trends
major variances
risks and opportunities
unusual movements

Summarize in clear, non-technical language."

✲ Step 3 — Turn Insights into Slide Content

Next prompt:

“Convert these insights into a structured presentation. Create slide titles + bullet points for each slide. Keep it concise and executive-level.”

You’ll instantly get something like:

- Slide 1: Financial Overview
• Slide 2: Revenue Trends
• Slide 3: Cost Drivers
• Slide 4: Key Risks
• Slide 5: Recommendations

✲ Step 4 — Generate Visuals Automatically

Use:

- Excel Copilot → create charts from your data
• Power BI → generate dashboards

or ask ChatGPT:
"Suggest the best charts for each slide."

This ensures:

- clarity
- better storytelling
- faster understanding for stakeholders

✲ Step 5 — Export to PowerPoint

Ask:

"Format this into a PowerPoint-ready structure with slide titles, bullet points, and speaker notes."

Then use:

- PowerPoint Copilot
• or copy-paste into your template

Your presentation is 80% done.

✲ Step 6 — Add Executive Commentary

Final prompt:

"Add CFO-level commentary and recommendations for each slide."

This is what separates the two:

- a data report from
- a decision-making tool

Most finance teams spend hours preparing slides…

When the real value is in:

- interpreting the data
- guiding decisions
- highlighting risks

I use AI almost every day in my finance work—building models, pressure-testing assumptions, drafting executive communications, working through complex financial structures.

And honestly? I have no idea if that makes me early, average, or behind.

I’ve been heads-down the past 12 months and recently realized I have very little visibility into how others are actually using AI day-to-day.

Not the headlines or vendor demos—the real workflows.

For example, I’ve found the Claude add-in for Execl especially useful working with existing models to create additional what-if scenarios to evaluate different options from a financial perspective. (I’ve also found a human in the loop and detailed eye is necessary, as Claude has changed some existing formulas erroneously.)

So I’m genuinely asking: if you’re in finance, ops, or a leadership role—how are you actually using it?

→ What’s changed in your workflow (if anything)?
→ What’s been surprisingly useful?
→ What’s been a dead end?

No polished takes needed—just honest ones. Especially interested in hearing from operators in it day-to-day.