Xero Launches XeroForce AI Workflow Builder for Small Businesses
Global accounting platform Xero has announced XeroForce, a natural language AI agent builder designed to automate financial workflows for small businesses and accountants. The tool allows users to create custom AI agents using simple prompts, eliminating the need for coding expertise while connecting Xero with third-party business applications.
According to the official Xero media release, the platform is currently in alpha and available to invite-only customers, with a broader general release planned later this year. The announcement came on May 14, 2026, from Wellington, New Zealand.
Diya Jolly, Chief Product and Technology Officer at Xero, stated that XeroForce combines decades of domain context with verified data to help deploy agents that automate financial workflows and deliver compliance visibility. The system is purpose-built for end-to-end financial operations rather than generic AI tasks.
Key capabilities include month-end close automation, ongoing reporting, tax document organization, purchase order validation, and payroll approvals. The agents can also handle long-running processes by responding to events like email replies or filing deadlines over days or weeks (which is actually how most accounting work happens in reality).
Unlike generic AI platforms, XeroForce includes audit trails logging every action for compliance and client trust. The tool also supports bulk workflows across multiple clients, addressing a critical need for accountants and bookkeepers managing hundreds of clients simultaneously.
CPA Practice Advisor reported on the launch, noting that XeroForce is powered by Xero OS, the company's AI-native financial operating system. Xero OS also powers JAX, Xero's financial superagent that delivers actionable insights and autonomous workflows with human professionals at the helm.
Ben Kurtz, Senior Accountant at Nortons Business Advisors, provided early feedback on the platform. He noted the potential to automate workflows across Xero and everyday apps, tailored to how their practice operates, freeing up time currently spent on manual processing.
The physical experience differs from typical AI chatbots. Users interact through natural language prompts rather than navigating complex menus or writing code. The interface connects apps, actions, rules, and schedules into automated processes shaped for specific firms, clients, or industries.
Industry context matters here. Xero has been building toward this agentic era through partnerships like its multi-year deal with Anthropic to integrate Claude into Xero. This allows users to bring financial data directly into Claude conversations for real-time financial intelligence.
However, the alpha status means the technology is still being tested. Invite-only access suggests Xero is carefully validating reliability before broader deployment. Financial workflows demand accuracy that generic AI tools often cannot guarantee without domain-specific logic baked in.
Whether small businesses actually adopt this workflow builder depends on pricing, ease of use, and whether the automation truly saves time versus creating new management overhead. The accounting industry has seen plenty of "revolutionary" tools that ultimately add complexity rather than reducing it.
The real test comes when accountants stop demoing and start billing for the work these agents supposedly save.
Artūras Malašauskas is an AI Systems Integrator with 20+ years of production-grade web engineering experience. He has designed, shipped, and scaled enterprise Python/PHP systems for logistics, SaaS, and public-sector clients. For the past year, he has focused exclusively on AI integrations: deploying open-source LLMs, building generative media pipelines (image, audio, video), and engineering multi-agent workflows for real production environments. His standard: reproducibility, security, cost-efficient inference—no vaporware. He documents and evaluates emerging AI tooling, separating verified capabilities from marketing noise. Technical editor at: muza-ai.eu, ai-verslas.lt, ai-naujinos.lt Connect on LinkedIn
Artūras Malašauskas is an AI Systems Integrator with 20+ years of production-grade web engineering experience. He has designed, shipped, and scaled enterprise Python/PHP systems for logistics, SaaS, and public-sector clients. For the past year, he has focused exclusively on AI integrations: deploying open-source LLMs, building generative media pipelines (image, audio, video), and engineering multi-agent workflows for real production environments. His standard: reproducibility, security, cost-efficient inference—no vaporware. He documents and evaluates emerging AI tooling, separating verified capabilities from marketing noise. Technical editor at: muza-ai.eu, ai-verslas.lt, ai-naujinos.lt
Comments