Earmark CPE

Earn CPE Anytime, Anywhere

ChatGPT

Boost Efficiency in Accounting with AI—No Coding Required

· ·

In today’s rapidly evolving accounting landscape, artificial intelligence (AI) is becoming an indispensable tool. Yet, many professionals hesitate to embrace it, believing that coding expertise is required. AI expert and accounting professor Dr. Mfon Akpan dispels this myth, emphasizing that strategic thinking—not technical skills—is the key to unlocking AI’s potential in accounting.

In a recent Earmark webinar, Dr. Akpan addressed common misconceptions about using AI in accounting. “Success in AI doesn’t require coding skills,” he asserts. “In fact, I’m good at prompting but terrible at writing prompts.” 

In other words, mastering AI is less about technical expertise and more about leveraging practical problem-solving skills that accountants already possess.

Measuring AI Success Through Efficiency

When discussing AI, many in the accounting field focus on its flaws—like making mistakes or producing imperfect outputs. Dr. Akpan encourages a shift in perspective. Instead of fixating on technical shortcomings, he suggests focusing on the efficiency and ease that AI brings to tasks.

An efficiency-first approach emphasizes finding ways to do less while saving time. “If you have 20 tasks to do in a workday and can eliminate five of them, that’s a win,” explains Dr. Akpan. “Or if something that used to take you 40 minutes now takes 20 minutes.” By simplifying tasks, accountants can become more productive and competitive.

He uses a compelling analogy: “It’s like having a Formula One race car but driving it at 15 miles per hour.” Many professionals are not utilizing AI to its full potential, often using it in basic ways rather than harnessing advanced methods that significantly enhance efficiency.

The Art of Effective Prompting

To illustrate how to unlock AI’s full potential, Dr. Akpan compares two approaches to the same task. A simple prompt like “Generate a monthly financial report comparing this month’s performance with the previous year” is straightforward but limited. The real power comes from sophisticated prompting methods like Chain-of-Thought and Tree-of-Thought prompting.

“I’m good at prompting but terrible at writing prompts,” Dr. Akpan admits. His secret? He asks the AI to write the complex prompts for him. By choosing the right prompting method and letting the AI handle the details, he achieves more comprehensive and accurate results.

Chain-of-Thought Prompting

Chain-of-Thought prompting guides the AI through a logical sequence of steps to solve a problem. This method involves breaking down a complex task into sequential steps, mirroring how accountants methodically approach financial analyses.

During the webinar, Dr. Akpan demonstrates transforming a simple prompt into a chain-of-thought prompt by asking the AI to write it:

Simple Prompt: 

Generate a monthly financial report comparing this month’s performance with the previous year.

Chain-of-Thought Prompt:

1. Define key financial metrics to compare (e.g., revenue, expenses, net income).
2. Gather this month’s financial data for each metric.
3. Retrieve the same metrics from the previous year’s corresponding month.
4. Calculate the differences and percentage changes.
5. Analyze the reasons behind significant changes.
6. Visualize the data using appropriate charts and graphs.
7. Provide insights and actionable recommendations based on the analysis.

By guiding the AI through these steps, Dr. Akpan ensures a more comprehensive and accurate report. He emphasizes, “I could not sit and write all of this, but you can ask the language model to do it for you, and it’ll do it for you within seconds.”

Tree-of-Thought Prompting

Tree-of-Thought prompting aids in problem-solving by breaking down complex decisions into branches. This allows the AI to explore different options and choose the best one, much like how accountants consider various scenarios when making financial decisions.

Dr. Akpan provides an example:

Tree-of-Thought Prompt:

Root Thought: Generate a monthly financial report comparing this month’s performance with the previous year.

Branch 1: Define key metrics.
  – What financial metrics should we focus on? (e.g., gross margin, net income, revenue, expenses)
  – How do these impact the overall financial health of the company?

Branch 2: Gather data.
  – Obtain this month’s financial data points.
  – Retrieve the same data points from the same month in the previous year.
  – Check for any missing data or adjustments needed.

Branch 3: Calculate and compare.
  – Should we focus on absolute values or relative percentage changes?
  – How do both perspectives provide insights?

Branch 4: Analyze positive and negative trends.
  – Are there positive changes? Negative changes?
  – What factors are impacting these changes? (e.g., internal operational changes, market fluctuations)

Branch 5: Visualize and report.
  – What graphs or charts would make the comparisons clear and easy to understand?
  – Should the report include line graphs, bar charts, etc.?

Branch 6: Provide insights and recommendations.
  – Offer specific recommendations for operational improvements or strategic decisions.

By considering different branches and evaluating the best approaches, the AI produces a more detailed and insightful report. “With Tree-of-Thought prompting, you’re asking the AI to look at different options and approaches to the particular task, and then it will choose the best one,” Dr. Akpan notes.

Practical Application in Accounting Workflows

Dr. Akpan demonstrates how these prompting techniques can be applied in real-world accounting tasks.

Creating Presentations

He explains how he used AI to create a PowerPoint presentation for the webinar:

  • He provided the webinar description and learning objectives to ChatGPT.
  • Asked ChatGPT to create an outline and generate PowerPoint slides with questions.
  • ChatGPT produced draft slides, including a title slide and content slides with key questions.

“I didn’t have to open PowerPoint or start making the slides from scratch,” Dr. Akpan explains. “Something that might have taken me 40–50 minutes took me about 15 minutes.”

Generating QR Codes

He also demonstrated using ChatGPT to create QR codes for his LinkedIn profile and his book:

  • Provided his LinkedIn profile URL to ChatGPT.
  • Asked it to generate a QR code linking to his profile.
  • Within seconds, ChatGPT produced the QR code, which he added to his presentation.

Simplifying Client Communication

Dr. Akpan shares a story about a former student who uses AI to simplify complex accounting jargon for clients:

“One of my former students who recently graduated… she said, ‘Yes, we use ChatGPT to help with client meetings.’ She uses AI to explain potentially complex accounting jargon to clients, finding better ways to express or explain concepts to someone who may not be well-versed in financial information.”

These practical applications showcase how AI can save time, improve output quality, and enhance client communication without requiring coding skills.

Embracing AI Without Coding

The same methodical approach that makes great accountants can make effective AI users. By focusing on efficiency, learning how to ask the right questions, and applying systematic review processes, accountants can turn AI into a powerful tool.

Dr. Akpan emphasizes the importance of using AI to discover its capabilities: “The more you use it, the more you can see how far you can push it and what it can do. If you’re not using it, you don’t know what it can do.”

He encourages accountants to shift their perspective on AI, viewing it as a means to reduce tasks and save time rather than expecting perfection.

Key Takeaways

  • Efficiency is Key: Use AI to reduce tasks and save time, increasing productivity.
  • Master Prompting Techniques: Utilize methods like Chain-of-Thought and Tree-of-Thought prompting to enhance AI outputs.
  • Leverage AI in Workflows: Incorporate AI into daily tasks to automate routine work and focus on higher-level analysis.
  • Continuous Learning: Regular use of AI tools leads to greater understanding and more effective application.

Embracing AI doesn’t require coding but a shift in mindset. By adopting strategic prompting techniques, accountants can unlock new levels of efficiency and effectiveness in their practice. As Dr. Akpan advises, start using AI tools to explore their capabilities and find out how they can transform your workflows.

Ready to transform your accounting practice with AI? Watch the full Earmark webinar to learn more practical implementation strategies and real-world examples of AI excellence in accounting.

An Accounting Firm Owner’s Guide to Strategic Technology Adoption

· ·

Is your accounting firm’s technology stuck in the past? In a world where clients expect seamless digital experiences and remote work is the norm, relying on outdated, disconnected software can be a recipe for inefficiency, frustration, and even lost business. But with so many options on the market, how do you choose the right tools to propel your firm forward?

In a recent Earmark Podcast episode, Blake Oliver shared his framework for strategic technology adoption. He argued that firms that intentionally select software to streamline operations, enhance client experience, integrate smoothly, and enable standardization will be best positioned to thrive.

Blake walked through the key software categories firm leaders need to consider, from proposal management to artificial intelligence (AI). He emphasized the importance of choosing tools that are easy to use, align with the firm’s unique needs and processes, and facilitate client collaboration.

Proposal Software

Blake recommended proposal software options that allow firms to quickly generate professional, standardized proposals, collect e-signatures and payments, and kick off projects seamlessly. “You cannot standardize the service delivery to your clients if you don’t have standard terms in your engagement letters,” he noted.

For example, Practice Ignition and Anchor allow firms to create templated proposals with standardized terms, pricing, and payment schedules. Clients can quickly review and sign off on engagements digitally, reducing friction and ensuring consistency across the board.

Practice Management

For practice management, Blake stressed the importance of workflow tools that centralize client communications, automate tasks, and provide visibility across the firm. With remote work now the norm, he argued, “If you’re in a remote environment, how can you work remotely without having workflow software?”

Platforms like Karbon, Canopy, and Client Hub offer client portals, task management, team collaboration, and insights reporting features. By standardizing processes and centralizing information in one system, firms can boost efficiency, transparency, and accountability, even with distributed teams.

Blake shared a cautionary tale from his experience, where choosing the wrong practice management tool cost his firm weeks of lost productivity. The lesson? Prioritize ease of use and team buy-in when evaluating options to ensure successful adoption.

General Ledger & Payroll

In the realm of general ledger and payroll, Blake advised firms to curate a lean tech stack of best-fit solutions. Instead of accommodating every possible client need, he suggested choosing one or two options that cover the bases for core client types, focusing on scalability, integration, ease of use, and reporting capabilities.

For the general ledger, that might mean standardizing on QuickBooks Online for most clients, with Sage Intacct reserved for those with more complex needs. On the payroll front, Blake highlighted Gusto and OnPay as user-friendly options that automate compliance and integrate with popular GL systems.

Blake emphasized the goal of going deep on a few core platforms rather than spreading yourself thin across a dozen different tools. By strategically limiting your tech stack, you can streamline training, support, and processes while still meeting diverse client needs.

Accounts Payable & Banking

Turning to bill pay, Blake highlighted the spectrum of solutions available, from all-in-one platforms like BILL for larger clients with complex approval workflows to more streamlined options like Relay for smaller businesses. He emphasized the key is to match the tool to the client’s specific needs and design efficient processes around it.

For example, a large nonprofit with multiple departments and strict controls might benefit from BILL’s advanced approval routing and audit trails. A small business, on the other hand, may prefer Relay’s simplified workflow and flat-fee pricing. The right fit depends on factors like transaction volume, number of approvers, and accounting complexity.

Whichever tool you choose, Blake stressed the importance of clear client communication and well-defined processes. Establish expectations around bill submission, approvals, and payment timelines upfront, and consider designating a dedicated team member to manage the AP queue and troubleshoot any issues.

Artificial Intelligence

Finally, Blake touched on the exciting frontier of AI, noting that ChatGPT’s new offering for teams, coupled with Microsoft’s significant investment in OpenAI, has made the technology more viable for accounting firms than ever. He advised listeners to start exploring use cases like drafting routine documents.

For instance, firms could leverage ChatGPT to generate first drafts of engagement letters, email responses, or work papers based on predefined parameters. By automating the initial content creation, staff can focus on more strategic work like analysis and advisory.

However, Blake cautioned against an “AI-first” approach. Tools like ChatGPT should augment human expertise, not replace it. He recommended starting with narrow, well-defined pilots and keeping humans in the loop to review and refine AI-generated content.

The Path Forward

Across all these categories, Blake underscored the importance of approaching technology decisions with intention and a focus on client needs. Flashy features may generate buzz, but the true test of any tool is how well it supports your firm’s service delivery and client experience.

By aligning your tech stack with your strategic priorities, designing efficient processes, and investing in training and change management, you can harness the power of modern software to drive meaningful results. The key is to start small, iterate often, and never lose sight of the humans at the heart of your business’s heart – your team and your clients. Ready to dive deeper into Blake’s strategic technology playbook? Listen to the full episode and start charting your firm’s path to digital success.

AI’s ‘Killer Function’: Personal Agents That Work for You

· ·

Sam Altman, the creator of ChatGPT, says that helpful agents will be AI’s ‘killer function,’ integrating deeply into our lives and acting as extensions of ourselves.

It sounds like science fiction, but you can start doing this now! In this clip from Episode 383 of The Accounting Podcast, I demonstrate how to create an AI agent using Central, a new feature of Zapier.

AI agents are a massive leap over today’s AI chatbots. Most popular chatbots can’t act autonomously. If you sign up for ChatGPT or Claude, you have to prompt it for everything you’re doing – copy-paste between whatever’s in your life and the bot. It’s a big hassle and wastes a lot of time.

But if you turn a chatbot into an agent, you give it the ability to act independently. Imagine a virtual assistant who can automatically respond to all the daily routine questions you get bombarded with.

For example:

| Hey, can I get an update on my tax return?

| When can I expect my financial statements?

| Please send a copy of your W-9 (or we won’t pay you)

Your AI agent has you covered, firing off personalized responses faster than you can say “accounts receivable.”

Or imagine an AI agent with access to your calendar that responds to meeting requests with the best times for you to meet based on your detailed instructions.

Sure, we have apps like Calendly, but these apps are limited and impersonal. For instance, I like to bunch my meetings, and Calendly doesn’t do that. I could tell my AI agent always to try to fit new meetings before or after an existing meeting. And it could do this by replying on my behalf to emails rather than me sending a link.

This is a big deal. Think about it – how many hours do you spend each week on repetitive tasks or answering questions? Now, you can start to automate them.

Zapier has built a tool, Zapier Central, where you can create your own AI agents triggered by the thousands of apps that already connect to Zapier.

I’ve been experimenting with having Central draft emails for me. I built an agent called “Email Assistant” and gave it access to my Gmail account. Then, I created a “behavior” with instructions to monitor my inbox for emails from our podcast contact form.

We get daily emails from listeners of The Accounting Podcast, and I read and respond to every single one. There are a few things that are annoying about the process.

  • The email comes from a different email address than the listener’s, so I have to copy/paste the listener’s email into the “To” field.
  • I have to add my co-host to the CC field so he’s in the loop.
  • I have to draft the email, which typically includes similar phrases. For instance, I start by thanking the sender for listening and writing in.
  • I tend to sign off in the same way every time, but I still need to type it because I don’t always use the signoff, and I don’t want it in my email signature

To get the Email Assistant to do all this for me, I gave it the following instructions:

When I receive a new email from TAP Contact Form, do the following:

– Create a draft reply in the same conversation thread
– Find the submitter’s email in the body and add it to the “To” field of the reply
– Draft a reply in the voice of Blake Oliver
– Start by thanking the sender for listening and writing
– Sign off with ‘Best, Blake’

Only draft replies to emails from the Tap Contact Form. Ignore emails not related to this.

Here’s what that looks like in Zapier Central:

When I do this task manually, after sending my reply, I copy the sender’s original email into my database of potential stories for my podcast (so I don’t forget to read it during our Listener Mail segment). Fortunately, my database, Notion, connects to Zapier. So, I added the instructions for my Email Assistant to get the AI to do that for me, too:

Then, please create a new database item in Notion. For the item’s name, make a name for the item that represents the topic of the message. Briefly summarize the listener’s question or comment in the notes field, and then put the listener’s name, email, and message in the body of the page.

This behavior triggers when I get a new email from the contact form. Then, it can create draft replies and database items in Notion through actions I’ve configured. Those are the only two things it can do – it can’t send the email to me. But it could if I wanted it to.

Here’s the agent thinking through what to do with a test email:

It worked!

Using AI Agents in Public Accounting

That got me thinking about how you could use AI agents in an accounting firm.

Let’s say that you’re tired of responding to requests from clients for information on how their tax return is going. You could create an agent with a behavior that says, “Every time I get an email asking about the status of a tax return, draft a reply letting the client know the status.”

But how would the AI agent know the status of the tax return? By connecting it to a spreadsheet – or perhaps your practice management software, if it’s sophisticated enough to work with Zapier.

Zapier lets you connect multiple data sources, such as Airtable, Google Sheets, Google Docs, Notion, etc.

Imagine if you had a Google Sheet where you tracked every tax return and the status of that return – not started, in progress, expected delivery date, any issues, etc.

You could then connect that data source to this AI agent and instruct it: “When a client asks about the status of their return, check the tax return spreadsheet and draft a reply with the status, who is working on it, and when we expect to complete it. Also, if the spreadsheet says we’re missing information, reply with a list of what we still need.”

You may need to add more detail about what columns to look in for each piece of information, but you get the idea. You’re programming the AI agent in plain English.

Using AI Agents in Corporate Finance

Here’s an example of how you could use an AI agent in corporate accounting. The Accounts Payable team. How often do they get the same email inquiries from vendors or customers?

Let’s say a vendor is asking about the status of the payment. Your email agent could watch for those emails and then automatically draft replies, letting them know when they will get paid or if something is holding up payment. You just have to connect your AP system to Zapier or sync the data to a spreadsheet that Zapier can watch.

You could create another behavior where if a customer requests a W-9, the AI agent sends an email with the signed W-9 attached. That’s one you could consider fully automating because it is low risk. You could choose to allow the agent to send the email without review.

Potential Uses Go Way Beyond Email

An important thing to note is that you don’t have to use this for email. This is just how I’ve been playing with it. You can trigger these agents with actions in thousands of apps. And these AI agents can then do stuff in thousands of apps.

There’s also a scheduling feature. This means triggers can be time-based, not just based on what happens in another app. You could schedule a behavior to run every day, every hour, every month, or every week.

Maybe that behavior is asking for a status update from your team on a particular project. For example, “If I haven’t received an update in so long, email the project owner and ask for an update.”

Now that I think about it, my own CEO job might be the first thing I automate.

AI Agents Are Happening Now

I don’t want you to think these AI agents are perfect; they are far from it. It’s brand new, so there will be things that don’t work right.

This behavior I showed you here is the one of three that worked well. The other two had some issues. So, don’t lose hope if you create an AI agent that doesn’t work exactly right. It’s going to take some time for these agents to work perfectly.

The important thing to take away from this is that AI agents aren’t just some far-off, futuristic concept – they’re a reality already starting to transform how we work right here and now.

I’ll keep sharing what I learn about AI agents, so subscribe to The Accounting Podcast and follow our LinkedIn page to see what I come up with.

Billable Hours vs. AI: The Battle for Accounting’s Future

· ·

Just as cloud accounting revolutionized the industry, AI is poised to be the next game-changer that will redefine the benchmarks for productivity and success in accounting. In a recent episode of The Accounting Podcast, David Leary and I explored the transformative potential of AI and its impact on the accounting industry.

The Cloud Accounting Revolution

To understand the potential impact of AI, it’s essential to look back at how cloud accounting transformed the industry. Cloud accounting reduced the time for traditional accounting and bookkeeping work by 80-90%. It forced firms like mine to adapt their business models and pricing strategies to remain competitive. 

As I mentioned in the podcast, “My career was in outsourced accounting. Cloud-based accounting cuts the time required to do traditional accounting and bookkeeping work by 80 to 90%. I couldn’t bill by the hour. If I did, I would not have a business.”

AI: The Next Frontier of Productivity

AI advancements in banking and accounting already show remarkable potential to boost productivity. JP Morgan Chase and Bank of America’s AI-powered cash flow forecasting tools have cut human manual work by 90%. David Leary highlighted this incredible statistic: “About 2,500 corporate enterprise clients are now using this tool, and they’ve cut human manual work. So you want to care to guess how much they’ve cut it by? 90%.”

The implications for accounting firms are profound. AI could lead to the end of billable hours and timesheets due to significant productivity gains. As I shared in the podcast, “We are using AI to do the base layer of work, and we are going to then have experts who review that. We’re going to turbocharge our staff.”

These advancements demonstrate how AI can dramatically increase productivity, setting new industry efficiency benchmarks as cloud accounting did.

Embracing AI: The Key to Success

Despite the potential of AI, the accounting industry appears hesitant to embrace this technology fully. Despite high awareness, an Accounting Today survey revealed that only 19% of accountants have used AI tools like ChatGPT for work and personal reasons. This hesitancy could put firms at a competitive disadvantage.

And even if they overcome their hesitancy, overwork impedes AI adoption in traditional firms. As I mentioned in the podcast, “The firms that are overloading their people, they’re not going to be able to innovate in this way because it takes a lot of time.” 

The Future of Accounting in the AI Era

AI, like cloud accounting before it, is set to revolutionize the accounting industry by redefining benchmarks for productivity and success. However, the industry’s hesitancy to embrace AI could hinder firms from realizing its full potential. Accounting firms that proactively invest in AI automation and adapt their business models will be better positioned to succeed in the AI era. At the same time, those who resist change may struggle to keep up. 

The future of accounting is here, and AI powers it. Are you ready? To learn more about how AI is transforming the accounting industry and what your firm can do to stay ahead, listen to the full episode of The Accounting Podcast. Don’t miss out on this insightful and thought-provoking discussion!