Connect with us

Accounting

Xero’s JAX said to tame gen AI hallucinations for acconting tasks

Published

on

Small business accounting platform Xero announced that it is beta testing a new generative AI assistant called Just Ask Xero, or JAX, which sports a control system that Diya Jolly, chief product and technology officer, said ensures accuracy and security. 

Speaking during Xero’s annual Xerocon event in Nashville, she noted that Xero is “no stranger to AI” as “it powers a range of our products,” but what’s different here is that JAX uses generative AI to automate tasks and provide guidance through a plain language interface. So while, before, someone might press a button that says “create an invoice,” then type in the line items and then type in the prices and then check the total, users would be able to simply tell JAX to create an invoice, and the AI will pull from the relevant data to deliver the result. 

“All of that is already in your email. You already typed it out once. Why do you need to type it again,” she said in a later interview, noting that it’s “just more natural” to interact with a plain language interface versus navigating through tabs and menus to get things done. 

Jolly said that accuracy is one of the key differentiators for its AI system. The tendency for large language models to give inaccurate information, particularly where numbers are concerned, is well known at this point. This has led to a certain degree of hesitation from professionals to deploy generative AI for serious accounting work (see previous story). Jolly nodded to these concerns, noting that “most of our competitors” are pursuing models that are very generic and prone to hallucinations.

“While there is power in generative AI, it has to be bound for accounting. … We cannot launch something in accounting where we do not have a high level of belief in its accuracy. This is our product. What are we doing if we’re not accurate?” she said. 

To this end, JAX was trained on a very specific set of data. More generic models such as those developed by Microsoft or Google are trained on massive data sets because it is intended for users to apply them to a wide set of functions. Jolly said that JAX was trained on more specialized data, such as being able to recognize an invoice or a quote, or understand terms like cash outstanding or accounts receivable. This helps the AI stay on task and avoid some of the confusion that can come from other models. 

Beyond this, however, the accuracy of the outputs are further bolstered by the fact that JAX was described as a hybrid AI that combines a large language model with machine learning and deep learning models. JAX itself does not actually do the work but, rather, acts as a go-between with the human user and the other AI models. 

So, if a user asked JAX for a cash flow projection over the next quarter, JAX would understand the request; then, it would convert this request to actual machine code which then gets passed onto the deep learning and machine learning AIs on Xero’s servers; these models would then perform the necessary calculations using the data they are allowed to access; the results, in machine code, would then be passed back to JAX, which would then translate the information back into plain language for the user to see. This is all part of what Xero called “JAX Assure” which Jolly described as a sort of control center that keeps the results accurate. 

“Because this is accounting, we want to be a lot more precise. So we can’t leave it up to the generative AI models to tell you cash outstanding. So then we use the machine learning, deep learning models to do the task. We are pretty confident, then, that we’re not going to get hallucinations… because, again, the AI models convert the language but the actual calculations happen with our [other] models,” she said. 

She also highlighted the AI’s mobile compatibility. People can access JAX through a mobile device, so they’re not tied to a desk, they can do what they need to do wherever they are. Jolly said she was often frustrated by the fact that she would go to meetings with “all these bills and receipts” but couldn’t do anything with them until she could get to her computer later. 

“So the fact that I just sent a quote or just created an invoice… the fact you can do it from email, you can do it from WhatsApp, it is extremely liberating and efficient for small business users as well as an accountant. So, being able to get paid, being able to make sure you’re staying on top of what you need to do to get your business moving, I think is cool, because believe it or not most of our businesses, when they have to send invoices or whatever at night, they forget,” she said. 

These features are only the beginning. Jolly, during her presentation, said that JAX, over time, will be in more and more of the Xero platform where it might be able to do things like check for anomalies or find specific types of transactions. Regardless of what it does, though, Jolly said the key differentiator will be its accuracy. 

“I think our accuracy will be our long sustaining [differentiator], like ‘hey we found a way to do gen AI that is accurate. And private,” she said. 

JAX is currently in beta. Those who are interested in taking part can click here.

Continue Reading

Accounting

PwC AI agent acts proactively to preserve value

Published

on

Big Four firm PwC announced new agentic AI capacities, including a model that proactively identifies areas of value leakage and acts inside the tools teams already use to fix them itself. 

The new solution, Agent Powered Performance, combines continuous AI-driven insight with embedded execution to address the problem of businesses only finding problems when they have already hurt performance. By actively monitoring and working inside the client’s existing systems, though, PwC’s agents can actively and autonomously address such issues. 

The software, which is supported by PwC’s recently released Agent OS coordination platform, is  embedded in enterprise systems to sense where value is leaking, think through the most effective performance strategies using predictive models and industry benchmarks, and act directly in tools like ERP or CRM software to make improvements stick. 

The system connects directly into ERP environments, continuously monitors key metrics, and acts inside the tools teams already use. For example, a supply chain agent might detect rising shipping costs and automatically reroute deliveries to reduce spend. Finance agents can spot and correct billing errors before they reach the customer. Clients typically see measurable efficiency gains in the first quarter, with continued improvements over time as the system learns and adapts.

“Too many transformations still rely on one-off pilots and stale data, stretching the gap from insight to impact and suffocating ROI,” said Saurabh Sarbaliya, PwC’s principal for enterprise strategy and value. “Agent Powered Performance flips the economics by distilling PwC’s industry transformation playbooks into AI agents that turn static insights into compounding gains, without rebooting each time.”

Agent Powered Performance is platform-agnostic and built on an open architecture so it can work across different LLMs based on client preferences and task-specific needs. It works with major enterprise platforms including Oracle, SAP, Workday and Guidewire.

Agent OS Model Context Protocol

PwC also announced that its Agent OS AI coordination platform now supports the Model Context Protocol, an open standard from Amazon-backed AI company Anthropic. 

By integrating this standard, agent systems registered as MCP servers can be used by any authorized AI agent. This reduces redundant integration work and the overhead of writing custom logic for each new use case. By standardizing how agents invoke tools and handle responses, MCP also simplifies the interface between agents and enterprise systems, which will serve to reduce development time, lower testing complexity, and cut deployment risk. Finally, any interaction between an agent and an MCP server is authenticated, authorized and logged, and access policies are enforced at the protocol level, which means that compliance and control are native to the system—not layered on after the fact. 

This means that agents are no longer siloed. Instead, they can operate as part of a coordinated, governed system that can grow as needs evolve, as MCP support provides the interface to external tools and systems. This enables organizations to move beyond isolated pilots toward integrated systems where agents don’t just reason, but act inside real business workflows. It marks a shift from experimentation to adoption, from isolated tools to scalable, governed intelligence.

Research Composer

Finally, a PwC spokesperson said the firm has also launched a new internal tool for its professionals called Research Composer, a patent-pending AI research agent embedded in the firm’s ChatPwC suite, designed to accelerate insight generation by combining web data with PwC-uploaded content. 

Professionals will use the Research Composer to produce in-depth, citation-backed reports for either the firm or its clients. The solution is intended to enhance the quality of client work by equipping teams with research and strategic analysis capabilities. 

The AI agent prompts users through a step-by-step research workflow, allowing them to shape how reports are packaged—tailoring the output to meet strategic needs. For example, a manager in advisory services might use Research Composer to evaluate white space opportunities across industries or geographies, drawing from internal reports and up-to-date market data.

Continue Reading

Accounting

Eide Bailly merges in Traner Smith

Published

on

Eide Bailly, a Top 25 Firm based in Fargo, North Dakota, is growing its presence in the Pacific Northwest by adding Traner Smith, based in Edmonds, Washington, effective June 2, 2025. 

Traner Smith’s team includes two partners and 16 staff members and specializes in tax compliance and advisory services. Financial terms of the deal were not disclosed. Eide Bailly ranked No. 19 on Accounting Today‘s 2025 list of the Top 100 Firms, with $704.98 million in annual revenue, approximately 387 partners and over 3,500 employees. 

Eide Bailly already has offices in Seattle, but hopes to grow further in the Pacific Northwest. “We’re pleased to welcome the talented team at Traner Smith to Eide Bailly,” said Eide Bailly managing partner and CEO Jeremy Hauk in a statement Monday. “Their expertise with high-net-worth individuals, real estate and privately held businesses aligns well with our strengths, and their client-centric approach is a perfect cultural fit. Having an office in Edmonds, Washington, is a great complement to our existing presence in Seattle. Together, we’re poised to deliver even greater value to families and businesses in the Seattle metro area.” 

“Joining Eide Bailly is a natural next step for us — it provides access to deeper technical resources in areas like state and local tax, national tax, succession planning and international tax while allowing us to continue the personalized service our clients value,” said Kevin Smith, a partner at Traner Smith, in a statement. 

“With this expanded support and platform, we’re excited to grow our reach, elevate what we do best, and help more clients than ever before,” said Shane Summer, another partner at Traner Smith, in a statement.

Eide Bailly has announced several other mergers in recent weeks. Earlier this month, it added Hamilton Tharp, a firm based in Solana Beach, California, and Roycon, a Salesforce consulting firm in Austin, Texas. In late April, it merged in Volpe Brown & Co., in North Canton, Ohio. Eide Bailly expanded to Ohio last year by merging in Apple Growth Partners. Last year, Eide Bailly also sold its wealth management practice to Sequoia Financial Group. The deal with Sequoia appears to be fueling the recent M&A activity. As part of the deal, Eide Bailly Advisors became part of Sequoia Financial, while Eide Bailly received an equity investment in Sequoia.

In 2023, Eide Bailly added Secore & Niedzialek PC in Phoenix, Raimondo Pettit Group in Southern California, Bessolo Haworth in California and Washington State, Spectrum Health Partners in Franklin, Tennessee, and King & Oliason in Seattle. In 2022, it merged in Seim Johnson in Omaha, Nebraska, and in 2021, PWB CPAs & Advisors in Minnesota. In 2020, it added Mukai, Greenlee & Co. in Phoenix, HMWC CPAs in Tustin, California, and Platinum Consulting in Fullerton.

Continue Reading

Accounting

BMSS announces investment, collaboration with Knuula

Published

on

Top 100 firm BMSS announced an investment in Knuula, an engagement letter and client documents software provider. The investment from BMSS came after successfully implementing Knuula over the past year to streamline its engagement letter process. It was after doing so that the firm’s leadership came to believe that Knuula could create complex client documents at an enormous scale, which was a huge need for the broader accounting industry. BMSS thought this presented a great opportunity to guide Knuula and help facilitate its growth. 

“We began working with Knuula in Spring 2024 to streamline our engagement letter process,” said Don Murphy, Managing Member of BMSS. “It quickly became clear that Knuula was not only a strong solution for us, but also an ideal partner in advancing industry-wide automation.”

While the specific terms of the deal were not disclosed, a spokesperson with Knuula said that, after this investment, BMSS and a collection of 21 of their partners now own 13% of the company. The investment represents not some passive revenue deal but an active collaboration between the two companies, with the spokesperson saying they will be working closely together on things like product development, new features, improvements, and networking.

The deal comes about a year after Knuula integrated with QuickFee, a receivables management platform for professional service providers, which allowed users to have engagement letters directly connecting to their QuickFee billing platform, tying the execution of the letter directly to the billing process. 

“We’ve long sought to partner with a firm focused on strategic innovation in the accounting space,” said Jamie Peebles, founder of Knuula. “To develop a perfect solution for large firms, it is ideal to have a partner that is willing to work closely together and iterate quickly. This requires constant feedback between our two teams. The IT team from BMSS worked with our development team constantly and helped us iterate rapidly. We also had consistent input from partners, manager, and administrative staff to help us make valuable changes to Knuula. BMSS was a perfect partner for us.”

Continue Reading

Trending