Get paid faster: How Intuit’s new AI agents help businesses get funds up to 5 days faster and save 12 hours a month with autonomous workflows

Join the event trusted by enterprise leaders for nearly two decades. VB Transform brings together the people building real enterprise AI strategy. Learn more


Intuit has been on a journey over the last several years with generative AI, incorporating the technology as part of its services at QuickBooks, Credit Karma,Turbotax and Mailchimp.

Today the company is taking the next step with a series of AI agents that go beyond that to transform how small and mid-market businesses operate. These new agents work as a virtual team that automates workflows and provides real-time business insights. They include capabilities for payments, accounts and finance that will directly impact business operations. According to Intuit, customers save up to 12 hours per month and, on average, will get paid up to five days faster thanks to the new agents.

“If you look at the trajectory of our AI experiences at Intuit in the early years, AI was built into the background, and with Intuit Assist, you saw a shift to provide information back to the customer,” Ashok Srivastava, chief AI and data officer at Intuit, told VentureBeat. “Now what you’re seeing is a complete redesign. The agents are actually doing work on behalf of the customer, with their permission.”

Technical architecture: From starter kit to production agents

Intuit has been working on the path from assistants to agentic AI for some time.

In September 2024, the company detailed its plans to use AI to automate complex tasks. It’s an approach built firmly on the company’s generative AI operating system (GenOS) platform, the foundation of its AI efforts.

Earlier this month, Intuit announced a series of efforts that further extend its capabilities. The company has developed its own prompt optimization service that will optimize queries for any large language model (LLM). It has also developed what it calls an intelligent data cognition layer for enterprise data that can understand different data sources required for enterprise workflows.

Going a step further, Intuit developed an agent starter kit that builds on the company’s technical foundation to enable agentic AI development.

The agent portfolio: From cash flow to customer management

With the technical foundation in place, including agent starter kits, Intuit has built out a series of new agents that help business owners get things done.

Intuit’s agent suite demonstrates the technical sophistication required to move from predictive AI to autonomous workflow execution. Each agent coordinates prediction, natural language processing (NLP) and autonomous decision-making within complete business processes. They include:

Payments agent: Autonomously optimizes cash flow by predicting late payments, generating invoices and executing follow-up sequences. 

Accounting agent: Represents Intuit’s evolution from rules-based systems to autonomous bookkeeping. The agent now autonomously handles transaction categorization, reconciliation and workflow completion, delivering cleaner and more accurate books.

Finance agent: Automates strategic analysis traditionally requiring dedicated business intelligence (BI) tools and human analysts. Provides key performance indicator (KPI) analysis, scenario planning and forecasting based on how the company is doing against peer benchmarks while autonomously generating growth recommendations.

Intuit is also building out customer hub agents that will help with customer acquisition tasks. Payroll processing as well as project management efforts are also part of the future release plans.

Beyond conversational UI: Task-oriented agent design

The new agents mark an evolution in how AI is presented to users.

Intuit’s interface redesign reveals important user experience principles for enterprise agent deployment. Rather than bolting AI capabilities onto existing software, the company fundamentally restructured the QuickBooks user experience for AI.

“The user interface now is really oriented around the business tasks that need to be done,” Srivastava explained. “It allows for real time insights and recommendations to come to the user directly.”

This task-centric approach contrasts with the chat-based interfaces dominating current enterprise AI tools. Instead of requiring users to learn prompting strategies or navigate conversational flows, the agents operate within existing business workflows. The system includes what Intuit calls a “business feed” that contextually surfaces agent actions and recommendations.

Trust and verification: The closed-loop challenge

One of the most technically significant aspects of Intuit’s implementation addresses a critical challenge in autonomous agent deployment: Verification and trust. Enterprise AI teams often struggle with the black box problem — how do you ensure AI agents are performing correctly when they operate autonomously?

“In order to build trust with artificial intelligence systems, we need to provide proof points back to the customer that what they think is happening is actually happening,” Srivastava emphasized. “That closed loop is very, very important.”

Intuit’s solution involves building verification capabilities directly into GenOS, allowing the system to provide evidence of agent actions and outcomes. For the payments agent, this means showing users that invoices were sent, tracking delivery and demonstrating the improvement in payment cycles that results from the agent’s actions.

This verification approach offers a template for enterprise teams deploying autonomous agents in high-stakes business processes. Rather than asking users to trust AI outputs, the system provides auditable trails and measurable outcomes.

What this means for enterprises looking to get into agentic AI

Intuit’s evolution offers a concrete roadmap for enterprise teams planning autonomous AI implementations:

Focus on workflow completion, not conversation: Target specific business processes for end-to-end automation rather than building general-purpose chat interfaces.

Build agent orchestration infrastructure: Invest in platforms that coordinate prediction, language processing and autonomous execution within unified workflows, not isolated AI tools.

Design verification systems upfront: Include comprehensive audit trails, outcome tracking and user notifications as core capabilities rather than afterthoughts.

Map workflows before building technology: Use customer advisory programs to define agent capabilities based on actual operational challenges.

Plan for interface redesign: Optimize UX for agent-driven workflows rather than traditional software navigation patterns.

“As large language models become commoditized, the experiences that are built upon them become much more important,” Srivastava said.

Similar Posts

  • Try on styles with AI, jump on great prices and more

    Whether you’re still on the hunt for the perfect summer maxi skirt, dreaming about a new fall jacket or starting your back to school shopping, our shopping tools can help you explore your personal style and get a good price. Here are a few ways you can use Google’s latest shopping features:Try clothes on, virtuallyAt I/O in May, we introduced our try on tool as a limited experiment in Search Labs, allowing shoppers to upload a photo of themselves and use AI to virtually try on clothes. Today, try on is launching in the U.S., letting you easily try on styles from the billions of apparel items in our Shopping Graph across Search, Google Shopping and even product results on Google Images.

  • Razer Pro Click V2 Vertical Review: A Hybrid Gaming Mouse

    Switching to a vertical mouse is a hard sell. Having to change how you use a mouse completely can be an intimidating task, especially with how unnatural the new hand position feels at first—you’re going entirely against the muscle memory you’ve spent years building up.One of the largest challenges to the switch is the initial loss of pointer accuracy. If you’re in an office setting, you may find yourself wandering around a bit or struggling to move your new mouse as quickly as you did before. But in a slow-paced setting like that, all you struggle with is a few mis-clicks or slightly slower navigation. If you try to make this transition with gaming, it’s far more jarring, and the consequences are much more immediately noticeable.But even if it’s difficult to adapt to, could vertical mice be the future of gaming? Razer’s new Pro Click V2 Vertical Edition is a hybrid productivity and gaming vertical mouse. Vertical mice typically cater to office workers, but the focus on gaming performance makes the $120 Pro Click V2 one of a kind.Desk PresenceThe Pro Click V2 Vertical looks, more than anything else, like a modern gaming mouse. It has the textured exterior, metallic highlights, and slightly organic, H.R. Giger-esque curvature typical of Razer’s design language. But everything has been shifted around. The curved, cutting thumb rest sits on top of the mouse instead of on the side. A flare juts out from the right side as a place to rest the underside of your hand. The gunmetal highlight sits at the peak of the mouse rather than between the two buttons. Even the USB port is vertical, a humorous attention to detail.It’s intentionally designed as a gaming mouse that just happens to be vertical. Aesthetically, the only downside is the minimal RGB lighting. With only one section of lighting that runs along the bottom of the mouse, RGB lighting fans might feel disappointed. Still, it’s bright, reactive, and has great color accuracy. It’s more than enough for me, especially with how customizable it is with Razer’s Chroma software.The Pro Click V2 Vertical has the same specs as the standard Pro Click V2, with a 1,000-Hz polling rate, a 2.4-GHz dongle that can be stored on the underside, Bluetooth multi-device connectivity, and a reprogrammable button on top. The only features lost are the mouse wheel’s horizontal scrolling and toggleable non-ratcheted rotation.This mouse includes two major productivity features: app-specific profiles and multi-device connectivity, and both work effortlessly. Razer Synapse immediately detected different software and changed the active profile in response, and pressing the button on the underside of the mouse swapped between paired devices instantaneously.Beyond that, Razer Synapse is as impressive as always. I consistently find the software to be one of the best and most intuitive on the market, and that’s the case here. All of the menus are simple and efficient, the settings can be changed in real time, and the adjustments all have tooltips and explanations to tell you exactly what you’re changing.Annoyingly, Razer Synapse has advertisements on the homepage, something I’ve complained about when reviewing SteelSeries products in the past. However, unlike Steelseries GG, these “recommendations” can be permanently disabled in the app’s settings.Performance and PracticeThe overall hand position of the Pro Click V2 Vertical is natural, but incredibly upright. While some vertical mice, like those from Logitech or Hansker, find a middle ground between a standard and truly “vertical” hand position, Razer opted for a nearly perpendicular shape. While this is technically an ideal ergonomic shape, it will be harder to adapt if you’re moving directly from a standard mouse, and might not be as comfortable during the adjustment period.It felt unnatural for the first week or so, and required practice to use comfortably and confidently. Once I had acclimated, my speed and accuracy were nearly at the same level as a standard mouse, although consistent use still felt clunky and unfamiliar compared to the horizontal mice I’d been using for most of my life.

  • Our first long-duration energy storage partnership

    Electricity powers modern life. And we’re accelerating a wide range of technologies, from enhanced geothermal to advanced nuclear to even fusion technologies, that can enable a future where on-demand electricity needs are met with clean energy, every hour of every day.Today, we’re adding another technology to our portfolio: long duration energy storage (LDES). Through a new long-term partnership with Energy Dome, we plan to support multiple commercial projects globally to deploy their LDES technology.Energy Dome’s novel CO₂ Battery can store excess clean energy and then dispatch it back to the grid for 8-24 hours, bridging the gap between when renewable energy is generated and when it is needed. With this commercial partnership, as well as an investment in the company, we believe these projects can unlock new clean energy for grids where we operate before 2030, helping meet near-term electricity system needs and moving us closer to our 24/7 carbon-free energy goal.By bringing this first-of-a-kind LDES technology to market faster, we aim to rapidly bring its potential to communities everywhere — making reliable, affordable electricity available around the clock and supporting the resilience of grids as they integrate growing amounts of renewable energy sources.Why it’s importantLithium-ion batteries, which typically store and dispatch power for 4 hours or less, have been critical for adding electricity capacity to grids and managing short-term fluctuations in renewable generation — when the sun isn’t shining or the wind isn’t blowing. Google’s support for these shorter-duration batteries has helped the grids we rely on, from Belgium to Nevada, meet peak electricity demand and reduce the need to ramp up fossil fuel power plants.But what if we could store and dispatch clean energy for more than a few hours, or even a full day? Studies by the Electric Power Research Institute show that LDES technologies can cost-effectively integrate a growing volume of renewables onto power systems and contribute to more flexible, reliable grids. The LDES Council estimates that deploying up to 8 terawatts (TW) of LDES by 2040 could result in $540 billion in annual savings globally, thanks in part to their ability to optimize grids.How the technology worksEnergy Dome’s novel approach to energy storage uses carbon dioxide (CO₂) held in a unique dome-shaped battery. When there’s an abundance of renewable energy on the grid, the system uses that power to compress CO₂ gas into a liquid. When the grid needs more clean power, the liquid CO₂ expands back into a hot gas under pressure, creating a powerful force — much like steam escaping a pressure cooker — which spins a turbine. This spinning turbine generates carbon-free energy that can flow directly back into the grid for durations ranging from 8 to 24 hours.Energy Dome has already signed contracts to build commercial scale projects in Italy, the U.S., and India. And their technology has already proven successful, having injected electrons into the Italian grid for more than three years, thanks to their commercial demonstration facility and now with their full-scale 20 megawatt (MW) commercial plant in Sardinia, Italy.Why scale is crucialLDES has the potential to commercialize much faster than some of the other advanced clean energy technologies in our portfolio. This means we can use it in the near term to help the electricity system grow more flexibly and reliably, alongside other tools we’re developing such as data center demand response.By supporting multiple commercial deployments of Energy Dome’s technology globally, we aim to bring this technology to scale faster and at lower costs. Beyond our long-term collaboration with Energy Dome, we plan to support a growing range of LDES technologies under development through both commercial agreements that can catalyze wider market adoption of more mature technologies, like Energy Dome’s, as well as earlier-stage investments.To remove barriers to the deployment and commercialization of LDES and other advanced carbon-free energy technologies, we’re also advocating for clean energy policies, ensuring that energy markets fully value firm, flexible carbon-free technologies, and advancing policy measures that enable infrastructure essential for grid decarbonization and energy security.We’re excited to take this first step with Energy Dome to unlock the full potential of LDES. Our partnership will strengthen grid resilience while enabling us to power our technologies, grow our economies and keep the lights on in our homes with 24/7 clean energy.

Leave a Reply

Your email address will not be published. Required fields are marked *