The AI-native FP&A platform brings expert-grade modeling to every finance team. Describe the plan in natural language, and Modeler builds it on live company data in minutes, calculated by Abacum’s Engine and approved by finance.
NEW YORK and BARCELONA, Spain, Oct. 13, 2026 /PRNewswire/ — Abacum, the AI-native FP&A platform, today launched Modeler, an AI agent that brings Agentic Modeling to finance teams. Starting from natural language prompts or existing spreadsheets, Modeler transforms initial inputs into live, fully functional business models instantly ready for execution.
Agentic Modeling is a new approach in which finance defines what a model needs to do, and an AI agent builds it. Instead of building a model line by line, teams set the requirements and the agent does the work. It selects the right structure from proven model blueprints, maps it to the company’s connected data and lays out the full logic for review. Work that has traditionally taken days or weeks of manual build now takes minutes, and the time it gives back goes where finance teams want it: analysis, scenarios and strategic decisions.
That time matters. Building and maintaining models is one of the most time-intensive parts of the finance function, and in most companies the models that do exist live with one or two people. When those people are busy, the business waits. When they move on, every model they own is one resignation away from nobody understanding it. Modeler is built to change both.
How Agentic Modeling Works
- Build live models in minutes – ask for the model you need, such as “Build me a P&L from my GL data.” Modeler scans the company’s connected datasets and builds a working model with calculations across actuals and planning versions, ready to plan from day one.
- Bring what you’ve built – upload an Excel file and Modeler reads its lines, sections and totals, then rebuilds that model on the data already connected to Abacum, so teams don’t start from scratch.
- Approve every plan – before anything is built, Modeler shows the full proposal, variable by variable, with the logic behind each one. Teams refine it in natural language, then approve or reject it. Nothing is saved without approval.
- Trust the math – Modeler proposes the structure and logic; Abacum’s deterministic calculation Engine performs every calculation, exactly as it does for models built by hand.
- Explain any model – ask any model to explain its own logic, line by line: what each variable is, how they connect and how every number is calculated. New team members get up to speed without reverse-engineering someone else’s work.
- Grow any model – add variables, and add, edit or remove sections in existing models, just by asking.
Time back for the work that matters
With Modeler, the hours that used to go into building go into using the model. A headcount plan the VP of Finance needs by Friday is ready the same morning. A new revenue model for the board starts as a request, not a blank canvas. A question about how a forecast is calculated gets answered on the spot, without waiting for the one person who built it. Finance teams move faster, and the expertise stays with the team.
Commenting on the launch of Modeler, Julio Martínez, Co-Founder and CEO of Abacum, said: “Finance has been told to do more with less for as long as anyone can remember. We think that promise has run its course. Modeler is about doing more with more: more models, built in minutes instead of weeks, by more of the team, with less lift than it has ever taken. The agent does the building, Abacum’s Engine still does the math, and finance still approves every model. What changes is how fast you get there, and who gets to build.”
Martínez continues: “Every finance leader knows the model that lives in one person’s head. That isn’t a modeling problem, it’s a resilience problem. When more of the team can ask for a model, see exactly how it works, refine it with natural language, and ask it to explain itself, the model belongs to the business. That’s what AI-native should mean: not AI bolted onto the side of a platform, but a finance team that is AI-native itself.”
What’s next
Modeler is the first step in Abacum’s agentic modeling roadmap. Later this year, it will bring complete workbooks into Abacum, including formulas and multi-tab files, and will extend editing deeper into existing models, so teams can refine what they’ve built as easily as they create it.
Availability
Modeler is available today to all Abacum customers as standard functionality, included in the Abacum platform at no additional cost. To see Modeler in action, visit https://www.abacum.ai/product/intelligence.
About Abacum
Abacum is the AI-native business planning platform. Built first for finance and extended to every department, Abacum holds a company’s data, business logic and context in one governed layer, where AI agents and teams plan the business together. Agents own the recurring workflows; people own the judgment. More than 500 customers in over 40 countries run their planning on Abacum, including DISH, ThoughtSpot, Strava, Acorns and Replit. Founded in 2020 and headquartered in New York, with offices in Toronto, Barcelona, Buenos Aires and the UK, Abacum is backed by more than $100 million from investors including Scale Venture Partners, Atomico and Y Combinator. Abacum is ISO/IEC 27001 certified, SOC 2 Type II and GDPR compliant, and is the first new FP&A platform NetSuite has accepted into its Built for NetSuite program in over a decade. Learn more at https://www.abacum.ai/
Media contact
Connor Mitchell
connor@mitchell-communications.com
Mitchell Communications
View original content to download multimedia:https://www.prnewswire.com/news-releases/building-on-abacum-intelligence-abacum-launches-modeler-and-brings-agentic-modeling-to-every-finance-team-302907146.html
SOURCE Abacum
