Earmark CPE

Earn CPE Anytime, Anywhere

AI Agents

QuickBooks Online’s Latest AI Update Could Save You Hours of Detective Work

· ·

Picture this: You’re reviewing a client’s profit and loss statement when travel expenses catch your eye. They’ve jumped 624% from last month. Is this legitimate business growth, a categorization error, or duplicate entries? Traditionally, this would mean hours of detective work, drilling into transaction details and cross-referencing receipts.

But what if an AI agent had already investigated this anomaly, traced it back to two identical $10,834 hotel charges, and presented you with a detailed report, complete with visual charts and actionable recommendations?

This feature is rolling out to QuickBooks Online users this summer.

In this episode of The Unofficial QuickBooks Accountants Podcast, Jim Dzundza, Staff Product Manager for the QuickBooks Accounting Automation team, explains how AI-powered error detection agents are transforming accounting workflows. But this isn’t about robots replacing bookkeepers. It’s about intelligent collaboration where AI handles time-consuming pattern recognition while accountants focus on analysis and client relationships.

From Program Manager to Product Developer

Dzundza’s journey at Intuit offers unique insight into how accountant feedback shapes product development. He started on the business development team working on desktop product partnerships, then moved to manage the ProAdvisor program for several years.

“Accountants have had a special spot in my heart,” Dzundza explains. “They are the key to us developing amazing products and amazing functionality.” His transition from the front-facing ProAdvisor program to backend product development wasn’t accidental; it was driven by impact.

“I felt like I could make a bigger impact by bringing this accountant perspective and finding a team within Intuit that really thinks about how accountants use and love the product,” he says. “And then focusing on where a lot of the pain is, to be honest. How can we help accountants reduce the pain of the work that they have to do?”

This accountant-first approach shows in every feature Dzundza shared on the podcast.

The AI Agent Revolution Begins

QuickBooks Online’s new platform introduces six specialized AI agents, each designed for specific accounting functions. The accounting, payments, and finance agents are currently available. Project management is in beta, while payroll and customer agents are coming soon.

The rollout timeline is aggressive but manageable. All new files created now automatically use the new platform. Starting in July, existing users can opt into the new experience. By September, everyone will see it, with the ability to opt out until the transition becomes mandatory at the end of September.

“We are daily reviewing feedback that is streaming in around all of the new UI, the new agents, everything coming out,” Dzundza emphasizes. “We’re implementing fixes and changes based on user feedback.”

This feedback period allows accountants to shape these tools rather than simply accepting what’s provided.

Eliminating Data Entry Frustrations

The accounting agent tackles three major workflow areas: getting transactions into the books, categorizing them, and reconciling accounts. Each advancement addresses real pain points accountants face daily.

PDF Statement Upload

For years, working with small banks meant manually keying transactions or using third-party tools like MoneyThumb. The new PDF statement upload feature completely changes this.

“You have the PDF and you go in to add that statement or upload those transactions in the same way you would upload a CSV today,” Dzundza explains. “And now you’re able to upload a PDF.” The AI extracts transactions directly from bank statement PDFs, eliminating the need for external conversion tools.

Enhanced Collaboration

Perhaps more revolutionary is the new collaboration feature available on Essentials and above. When you encounter a transaction needing clarification, you can ask questions directly within the bank feed and send clients a magic link via email or text.

“They can go on their phone and answer the question,” Dzundza notes. “They can answer it from wherever without having to log into QuickBooks.” Once clients respond, the AI automatically updates its categorization recommendations based on that context, creating a feedback loop that improves accuracy for future similar transactions.

This addresses a major frustration: forcing business owners to log into QuickBooks just to answer simple questions about transactions. It also gives accountants control over their books while still gathering necessary context.

Reconciliation Gets Smarter

The reconciliation process receives similar AI enhancements, with tools launching in mid-July. Like bank feeds, reconciliation now supports PDF extraction with a crucial enhancement: when the AI can’t extract everything accurately, it flags questionable areas for human review.

“Our goal for this one is 100% accuracy,” Dzundza explains. This hybrid approach, combining AI speed with human verification, ensures accuracy while eliminating manual data entry.

The new reconciliation interface organizes information into logical sections: cleared transactions that matched one-to-one, flagged one-to-many matches requiring review, and AI recommendations for transactions that should potentially be excluded or unposted.

This addresses common reconciliation headaches like duplicate detection. As Dzundza discussed with host Alicia Katz Pollock, it’s easy to upload a receipt and then also accept the same transaction from the bank feed without noticing the duplication. The AI now surfaces these duplicates automatically, eliminating manual scanning for errors.

The Anomaly Detection Game-Changer

The most sophisticated feature is the accounting agent’s anomaly detection, which transforms financial statement review from manual line-by-line scanning to intelligent pattern analysis.

How It Works

The system analyzes 13 months of historical data, comparing the most recent complete month against established patterns to identify accounts that deviate significantly from normal behavior. But it’s smarter than simple variance detection. It considers each account’s historical volatility. Accounts with consistent monthly variation won’t trigger alerts for normal fluctuations, while stable accounts get flagged for even modest deviations.

“It looks over the past 13 months, and then it looks at the most recent complete month,” Dzundza explains. “And it will tell you if this month’s total seems off on either the balance sheet or P&L.”

Professional-Quality Investigation

When the system detects anomalies, the AI conducts detailed investigations using what Dzundza describes as “customized prompts we designed in partnership with accountants.” These prompts guide the AI to analyze transaction patterns, identify common characteristics, and surface potential root causes.

Travel expenses are a perfect example of this capability. When the AI flagged a 624% increase in travel expenses, it didn’t just note the variance; it traced the increase to two identical $10,834 hotel charges from the same vendor, immediately raising the question of whether these were duplicates or legitimate separate transactions.

Seamless Integration

The feature integrates directly into standard financial statements through subtle blue sparkles next to affected line items. Clicking a sparkle opens a detailed analysis directly in context, allowing investigation without leaving the familiar report format. The sparkles don’t print when you export reports, maintaining clean client deliverables while providing powerful review capabilities.

Actionable Reporting

The AI generates professional-quality PDF reports that serve as both investigation summaries and work papers. These reports include visual charts showing the anomaly, detailed root cause analysis, supporting data points with reference numbers for easy transaction lookup, and comprehensive narrative explanations of findings.

As Katz Pollock notes, “this is something I would be very happy to just send to my client.”

The Partnership Model That Works

These AI updates aren’t about replacing accountants, but about elevating their work.

“It’s not about replacing jobs or anything like that,” Dzundza emphasizes. “It’s really focused on creating tools that make people more efficient in getting their work done.”

As Katz Pollock summarizes, “this is in no way taking your job. All this is doing is calling your attention to things that it’s noticed in a way that you would not have access to just by looking.” The technology provides pattern recognition and initial investigation, but professional judgment about significance, cause, and appropriate action remains firmly in human hands.

Your Voice in the Development Process

Dzundza stresses that development teams are reviewing user feedback daily and implementing changes based on that input.

This gives accounting professionals a unique opportunity to actively shape these tools. The key is providing constructive, actionable feedback with specific details rather than general complaints.

The Future of Accounting Practice

Technical proficiency with AI tools is becoming as important as traditional accounting skills. Accountants who embrace this partnership will find themselves elevated from data processors to strategic advisors, spending less time hunting for errors and more time interpreting their significance for clients.

The collaboration model redefines what it means to be an accounting professional in an AI-enhanced world. The accountants who thrive will be those who view AI as a powerful research assistant rather than a threat, focusing their expertise on the strategic analysis and client relationships that technology cannot replace.

As these AI agents roll out over the coming months, you have the opportunity to be part of shaping the future of accounting practice. Listen to the full episode to hear Dzundza’s complete demonstration of these features, understand the implementation timeline, and learn how to provide constructive feedback that will help refine these tools for maximum benefit to accounting professionals.

The future of accounting is being written now. Make sure your voice is part of that conversation.

Alicia Katz Pollock’s Royalwise OWLS (On-Demand Web-based Learning Solutions) is the industry’s premier portal for top-notch QuickBooks Online training with CPE for accounting firms, bookkeepers, and small business owners. Visit Royalwise OWLS, where learning QBO is a HOOT!

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.