AI Revolutionizing Accounting Practices Today
Accountants have a wealth of new avenues to apply artificial intelligence (AI), as capabilities for language processing, decision-making, and automation become more accessible than ever.
"There are so many new tools," observed Tricia Katebini, CPA, a partner at GRF CPAs & Advisors in Bethesda, Md. She has been instrumental in helping her firm implement numerous new AI-based tools. "It’s nice to see, but it’s overwhelming."
To cut through the hype and the wide array of new options, the JofA consulted six CPAs to share their most interesting AI use cases. These range from customized solutions to off-the-shelf software products. (Refer to the section "How to Determine AI Technology Needs" for more insights).
Here are their stories.
Case 1 Snail Mail Automation
Karl Spanbauer, CPA, is the controller of the not-for-profit Capital Area Food Bank, which supplies approximately 60 million meals annually to people around Washington, D.C.
Upon taking the job, he faced a significant annoyance: physical mail. His small accounting team was inundated with vendor invoices, tax notices, statements, and more.
"I lost a couple of documents. It was literally hundreds of pieces of mail," Spanbauer recalled. "I knew we had to automate it somehow."
Leveraging his experience with Microsoft Power Automate and other software, Spanbauer developed a custom solution to scan, summarize, and respond to mail.
Here’s how it operates:
- Staff members run all business-related mail through a scanner.
- The scanned file is automatically saved to a shared drive.
- An image analyzer extracts the text from the image.
- The text is analyzed by a secure large language model (LLM), which generates a summary.
- A ticket is created in Jira, the team’s workflow system, containing the summary and the original mail.
- The team addresses the tickets, responding to the mail as necessary.
Spanbauer has since added further automations to the system, simplifying tasks like looking up the status of scanned invoices and other follow-up actions.
Case 1 at a glance
- Degree of difficulty: Spanbauer drew upon extensive experience with Power Automate and other tools. While the solution was quick to implement, it was built on months of prior work connecting systems and data.
- Cost: The project incurred no additional implementation costs; it utilizes the team’s existing licenses.
- Payoff: The team now processes mail in 20-minute sprints during "Mail Mondays," saving about four hours of total staff time per week.
- The takeaway: The project succeeded because Spanbauer already had a robust digital environment; he just needed a method to integrate postal mail into it. "AI can’t interact with a piece of paper sitting on my desk. I had to get that piece of mail into that ecosystem," he explained.
Case 2 Technical Accounting Memos
Glenn Hopper serves as head of AI research development at Eventus Advisory Group in Memphis, Tenn. His firm caters to a mix of private companies and small-to-midsize public companies, offering services like fractional CFO and controllership roles.
One of his recent projects involves a specialized bot capable of drafting technical accounting memos.
"We get asked to do these accounting memos all the time," Hopper said. For instance, a memo might address goodwill impairment in an acquisition. It’s challenging because, he noted, "You have to get very technical, and you want to make it clear and understandable."
Using his generative AI expertise, Hopper took the organization’s collection of accounting memos and prepared them for LLM analysis through a technique called retrieval-augmented generation (RAG).
"We’ve been writing these forever," Hopper mentioned, "and we have a style we use for them."
This process involved dividing the memos into smaller, topically focused "chunks" that are easier for an LLM to process. Hopper then ran these chunks through vectorization and stored them in a vector database using OpenAI technology.
The result is a content repository the bot can use to create a "coherent and contextually relevant response," Hopper stated. The memo generator is powered by OpenAI’s Assistants API platform, which enables companies to build advanced, customizable bots.
Hopper added that he tried to "pound out any possibility for hallucination," referring to generative AI's tendency to invent facts when it cannot find the required information. "I think we’ve minimized it a lot by giving it very specific examples to refer to, very specific instructions," he said. This "fine-tuning" process involves exposing the customized bot to hundreds of examples, though Hopper noted he couldn't disclose more details as the specifics are proprietary to Eventus.
Once the tool generates an accounting memo draft, Eventus ensures a "human in the loop" reviews and corrects the memos as needed.
"The people who are using it are kind of blown away — and for many of them, it was their first foray into even using ChatGPT," he shared.
Case 2 at a glance
- Degree of difficulty: This was a highly customized implementation of OpenAI’s technology, requiring about 60 hours of Hopper’s time and deep expertise.
- Cost: Beyond ChatGPT license costs, the memo-generating bot and other advanced bots can incur charges of several dollars per run. Paid ChatGPT versions start at $20 per month for individuals and $25 per user for teams.
- Payoff: Hopper estimates that drafting accounting memos has gone from a four-hour task to a 30-minute task, including careful human review. Hopper has also created other bots for tasks like analyzing Forms 10-K.
- The takeaway: The memo bot was a success, but it wouldn't have been possible without Hopper’s expertise. For many other organizations, waiting for a vendor to develop an off-the-shelf product might be more cost-effective. "It takes time to do, and you need to have a certain skill set to do it," Hopper said. "It’s not cheap to get these things done."
Case 3 Marketing The Business
Barrett E. Young, CPA, is the marketing partner at GWCPA in La Plata, Md., a firm focused on helping family-held businesses prepare for leadership transitions. Since joining in 2017, Young has led the 15-member team to better utilize technology, including ChatGPT and related technologies over the past year.
The firm has even deployed its own client-facing tool: the GWCPA Generations Advisor, a customized ChatGPT deployment offering advice on ownership transitions. This custom GPT requires an active ChatGPT license but doesn’t incur per-use costs, as it's less complex than the Eventus bot previously described.
"I’m using ChatGPT every night when I have ideas in my brain at two in the morning," Young said. "I’m asking it questions and making notes, ‘What if I gave that to my customers?'"
Developing this type of custom GPT is relatively straightforward: The creator provides written instructions to ChatGPT, including the bot's purpose, response tone and structure, and other guidelines.
The goal was to create "something I could give away to our target audience that would start conversations and add value in their lives," Young explained.
Young enhanced the custom GPT by uploading GWCPA’s marketing materials. Custom GPTs can be instructed to refer to information or imitate the style of user-uploaded documents—another form of the RAG approach. To gain access, users simply sign up for GWCPA’s free marketing email list, which Young also uses to send weekly prompt ideas. The hope is that the custom GPT will answer basic succession planning questions, raising GWCPA's awareness and enabling deeper conversations when prospects are ready to meet.
Case 3 at a glance
- Degree of difficulty: Generations Advisor was relatively quick and easy for Young to implement, as he had already created a few custom GPTs for personal use. These simpler custom GPTs can be created within the ChatGPT interface using plain-language instructions.
- Cost: Creating a custom GPT requires a paid ChatGPT subscription, costing $20 or $200 per month, depending on the access level needed.
- Payoff: Subscribership for Young’s mailing list has steadily grown, with the custom GPT contributing about 50 new members in the past three months. While the audience is relatively small, Young says it’s reaching the right people. "One or two clients from that makes the entire thing worth it because we’re high-value, high-touch services," he stated.
- The takeaway: Generations Advisor is a light customization of the core ChatGPT project, leveraging the platform’s abilities to create a useful client tool that Young hopes will increase interest in the firm’s services.
Case 4 Data Analysis With AI Assisted Coding
As a consultant for executives and companies, Don Tomoff, CPA, a director at Invenio Advisors in Cleveland, has used ChatGPT for coding and analysis, saving time and money and enabling more efficient project execution.
"I used to outsource coding for projects, and I haven’t had to do that since January of 2023," Tomoff said. "That’s been just a huge win."
He now asks platforms like ChatGPT to generate code for tasks in Excel and other software. For example, he recently needed code to find a specific piece of text and delete all rows above it in an Excel spreadsheet, regardless of where it appeared. Tomoff described the problem in natural language to ChatGPT, and it returned functional Visual Basic (VBA) code. Other models like Anthropic’s Claude or Google’s Gemini have similar capabilities. For a prompt example used with Claude, see the section "Claude AI Prompt for VBA."
Tomoff breaks his requests into multiple stages, especially for larger projects. He asks ChatGPT what steps are required for a task, then instructs it to write code for each step. If the code is faulty, he can describe error messages and ask for revisions.
Outsourcing coding previously cost up to $150 per hour, or up to $2,000 for a typical project, Tomoff noted. Moreover, the time to develop, test, and improve solutions has dropped from days to hours, he said.
"You want to explain as precisely as you can what you want," he advised. "You don’t want to eat the elephant in one effort, because it will stop on you if you give it too much to digest. It’s iterative."
Brianne Smith, CPA/PFS, Ph.D., a financial adviser, managing member of her own accounting firm, and assistant professor of accounting at Auburn University at Montgomery, Ala., offers similar advice to her accounting students using ChatGPT for four phases of data analysis: "Ask the question, master the data, perform the analytics, share the story."
Smith explained: "You wouldn’t load ChatGPT and ask it to do all four things at the same time — but we would focus in on various areas and chunk them out into intermediary goals at the end."
ChatGPT and other tools can also analyze and transform files directly, not just generate code for users.
Case 4 at a glance
- Degree of difficulty: Low, provided the user has some familiarity with generative AI bots. The key is describing the problem specifically and having the patience to experiment and troubleshoot.
- Cost: Code generation is possible with free versions of major generative AI models but may be more convenient and powerful with paid versions.
- Payoff: Tomoff can now tackle more complex projects without outside help. "Projects that I either would not undertake or would take too long that I would undertake, I’m doing in minutes," he said.
- The takeaway: Embrace the bot as an extension of your abilities, Tomoff advised. "If you’re an accountant, you no longer can say, ‘I don’t know how to do this,'" he stated.
Case 5 Brainstorming And Research
LLMs can be powerful research assistants—when used correctly.
When Tomoff researches a topic, he might feed an outline into ChatGPT or Perplexity, the LLM-based search engine. He’ll ask: "What other areas would you add, and why would you add them?"
The answers can highlight research areas he may have overlooked, and follow-up questions can provide basic education in those areas. The power, Tomoff suggested, lies in the volume of ideas the bots can produce.
"People will say it’s not any more creative than you and me," he said. "It can sit and come up with ideas 100 times faster." He also pointed to ChatGPT’s recent implementation of a "deep research" option, a more powerful research tool for paid users.
Still, Tomoff cautioned that chatbots will only get users 90% of the way to an answer. Due to the risk of hallucinations, the user must still confirm any facts taken from the software’s responses.
Meanwhile, a new class of research tools is tailoring LLMs to accounting needs. Young’s firm recently started subscribing to Ask Blue J, whose bot focuses specifically on federal and state tax laws. It can return answers and citations for specific, detailed tax questions. The software can also generate memos and emails to clients. But it has some kinks. The answers are "95%" factual, Young said, but the model often struggles with accurate calculations involving frequently changing, inflation-adjusted figures.
"I’m always telling my staff, ‘Double-check that,'" he said.
Case 5 at a glance
- Degree of difficulty: Chatbots are intuitive research tools, but safeguarding against hallucinations requires both domain knowledge and experience with the bots.
- Cost: Free versions of chatbots can help with brainstorming and research. Costs for more advanced or profession-specific implementations will vary.
- Payoff: At best, chatbots can help accountants quickly answer questions and identify new research areas. "This is the tax manager I always wish I had, where I could ask any question and not get judged," Young said.
- The takeaway: Chatbots are not genies that can magically answer any question, but they can be tools for extending an individual’s knowledge. "It just augments what you know," Tomoff said.
Case 6 Audit Automation And Assistance
Katebini is an adviser to not-for-profits at GRF CPAs & Advisors, where she’s helped navigate the recent flood of automation and AI-powered tools, especially for audit uses.
The firm recently started using Trullion’s Audit Suite, which offers a range of useful features. The platform can:
- Search documentation for evidence related to an audit sample. "You’re not scouring through 80 pages of a bulk PDF. It’s very easy in that respect," Katebini said. The technology helps staff quickly identify if evidence is lacking for a particular audit point.
- Extract summaries from documents such as board minutes and lease agreements.
- Automate elements of financial statements, including footing statements and tying back disclosures to balances on those statements. "Our production team doesn’t have to go through the process of manually footing everything," Katebini said.
Trullion is one of many audit-focused products on the market. Another product, the AICPA’s Dynamic Audit Solution, analyzes large datasets to identify patterns and potential risks. Other products can automatically search for discrepancies and missing data or easily reformat data if sent in the wrong format.
"It’s the press of a button for us now," Katebini said.
Taken together, the firm’s new tools are improving staff’s ability to complete high-level analysis and build client relationships.
"Our staff is so inundated, there’s so much work to be done, it’s hard to take a step back and talk with your client sometimes, and technology advancements in assurance engagements is creating efficiencies to allow us more time to advise," Katebini stated.
Case 6 at a glance
- Degree of difficulty: Companies increasingly offer off-the-shelf products, but identifying and implementing solutions require familiarity with the technology and its applications, as well as project management expertise.
- Cost: Varies by product.
- Payoff: Substantially increased efficiency in managing and generating documentation.
- The takeaway: There’s a new generation of technological solutions and an emerging role for finance technologists to implement them.
How To Determine AI Technology Needs
Navigating the growing variety of artificial intelligence (AI) technology options can be challenging. Tricia Katebini, CPA, a partner at GRF CPAs & Advisors in Bethesda, Md., mentioned she spends so much time on technology that, "I’m a person in the firm that has been designated to head up and lead the technology implementations, the vetting."
Here’s how Katebini suggested identifying and implementing new solutions:
- Identifying pain points: Instead of looking for what "looks cool," Katebini said, the firm began by asking staff about the tasks and work that were most time-consuming and unexciting—such as creating note disclosures or getting data in the right format. "How can we solve that problem?"
- Seeking solutions: The team looks for solutions, including by asking vendors directly. "We’re bringing our pain points and problems to our vendors, too, and they’re very willing to listen."
- Making a choice: The right tool is a matter of cost, utility, and compatibility with the rest of an organization’s tech stack.
Consulting on technology implementation can even become a line of business for a firm, said Brianne Smith, CPA/PFS, Ph.D., who runs her own accounting practice and a financial advisory firm in addition to being an assistant professor of accounting at Auburn University in Montgomery, Ala.
"My firm and other firms are starting to consult on this type of process," Smith said. "We make sure that they have proper security and privacy. We also recommend various tools for pain points."
She and others suggested starting small with AI—even just experimenting for personal uses—and asking others for help and ideas along the way.
"There’s a whole community. We are all very willing to collaborate and talk about what tools we use," Katebini said. "It’s kind of exciting to be at the crossroads."
Claude AI Prompt For VBA
Below is an Invenio Advisors LLC prompt instructing the Claude AI model to create a Visual Basic (VBA) bot to move items from one list to another in Excel.
Prompt Structure
ClaudeAI PROMPT to move items from a list to another list (VBA)
You are an Excel VBA expert. I would like your help in creating a VBA macro that will MOVE (not copy) rows from one table to another when they’ve been checked. Specifically:
- Source worksheet: {INSERT WORKSHEET NAME} with table named {INSERT EXCEL TABLE NAME}
- Destination worksheet: {INSERT WORKSHEET NAME} with table named {INSERT EXCEL TABLE NAME} (create these if they don’t exist).
- The destination table should start at cell A10 if it needs to be created
- Move only rows where a checkbox in the last column is checked
- Transfer all columns EXCEPT the last 3 columns from the source table
- Prevent duplicates based on the video title (column 2) in the destination table
- After moving a row, DELETE it from the source table
- Include error handling for cases where tables don’t exist
- Alert the user with a message upon completion
The macro should first check if items are already in the saved list before moving them.
Once you have created the code, please advise if you have any recommendations for improvement. I will then let you know if I want to make any changes to the code you provide.
After you complete this task, please provide instructions on how to implement the process in my workbook. Take a deep breath and let’s do this!
{INSERT WORKSHEET NAME}: ExcelTips_VideoList
Source: Invenio Advisors LLC
About the author
Andrew Kenney is a freelance writer based in Colorado. To comment on this article or to suggest an idea for another article, contact Jeff Drew at Jeff.Drew@aicpa-cima.com.
Learning Resources
Learn how to use ChatGPT to streamline your workload, save time, and boost your overall efficiency.
CPE SELF-STUDY
Ethics in the World of AI: An Accountant’s Guide to Managing the Risks
This webcast discusses the current uses of AI in business, reviews nine risk areas, and provides practical suggestions to address these risks effectively.
June 4 and Aug. 5
WEBCAST
Learn what organizations should consider when implementing AI solutions.
June 16, Gaylord National, National Harbor, Md.
CONFERENCE
With nine tracks of expert content, you’ll gain exclusive insights, develop practical skills, and walk away with tangible guidance to evolve at your own pace. AICPA & CIMA ENGAGE 25 will be held at the ARIA in Las Vegas and is also available online.
June 9—12
CONFERENCE
Not-for-Profit Industry Conference
The conference, which will be held at the Gaylord National in National Harbor, Md., includes AI-related sessions on AI strategy and governance, advanced automation techniques using RPA and AI, and the C-suite’s road map to integrating AI in financial operations.
June 16-18
CONFERENCE
For more information or to make a purchase, go to aicpa-cima.com/cpe-learning or call 888-777-7077.
AICPA And CIMA Member Resources
Articles
"What AI Can Do for Auditors", JofA, Feb. 1, 2024
