What's new in Abacum

See the latest new features, improvements, and product updates

👁️ Preview the plan before AI builds your space
yesterday

👁️ Preview the plan before AI builds your space

New You now have more control over the spaces Abacum Intelligence builds for you. Before anything is created, it drafts a proposal of every block it intends to build, so you can make sure the space uses the right versions, metrics, dimensions and timeframes.

✨ What's new

  • Review before you build: the proposal preview shows each block with the variables, versions, dimensions and timeframes it will use.
  • Refine in plain language: ask for changes like "compare against Budget instead of Forecast" or "add headcount by department", and the proposal updates. Nothing is built until you approve.
  • Start from the Agent: you can now create a space by asking the Agent, not only through Spaces.

⚙️ How it works

  • Click Create space, choose Generate with AI, write your prompt and click Draft proposal. Or ask the Agent directly, for example: "Build me an OPEX space by department for this year." 
  • Review the proposal, click Adjust to make changes, and Approve when it's right. 
  • It all runs in the Agent panel, so you can keep working while it plans.

Learn more about creating spaces with AI.

Reporting 

🧹 Clean up your space list in one go
a week ago

🧹 Clean up your space list in one go

Improvement You can now select several spaces, subspaces or whole sections from the space list and delete them in a single action. It's the quickest way to clear out old spaces after a reorganisation or at the end of a planning cycle.

What's new

  • Multi-select: tick spaces, subspaces or a section. Selecting a parent space includes its subspaces.
  • Bulk delete: delete up to 100 spaces at once from the bar at the top of the list.
  • Clear confirmation: see every space that will be deleted, with its full path, before you confirm.

Try it now

  1. Open the space list and select the spaces you want to remove.
  2. Click Delete in the bar at the top.
  3. Check the list in the confirmation and click Delete spaces.

Learn more in the Abacum Academy. 


Reporting 

🔄 Connect any version to any other version
a week ago

🔄 Connect any version to any other version

You can now use any version as the Switchover source of another, so a forecast can build on another forecast, a budget can roll into the next, and more.

✨ What's new

Switchover source now works across every version type. A budget can inherit from a forecast, a forecast from another forecast, a budget from another budget, or a forecast from a budget. Whatever planning structure you need, you can point one version at another so it carries the source data up to the switchover date and continues with its own data after it.

⚙️ How it works

Open the version you want to configure and click Edit. In the Switchover section, select another version under the Version field. The list includes both your forecasts and budgets. Save, and your version references the selected source up to the switchover date.

Learn more in the Academy: Build a version on top of another

📅 Weekly models: plan your cash week by week
3 weeks ago

📅 Weekly models: plan your cash week by week


A business can look healthy on a monthly view and still run short of cash in the middle of the month. Build weekly models right next to your monthly ones and see those gaps coming.

What's new
When you create a model, you can now choose Weekly instead of Monthly. A weekly model shows one column per week and rolls up into months, quarters and years, so you see the weekly detail and the bigger picture in one place. It's built for the 13-week cash flow forecast, and works just as well for weekly revenue or weekly KPIs.

Weekly models work with the rest of Abacum. You can enter weekly inputs, pick the exact week your forecast starts, feed weekly numbers into your monthly P&L, and report by week with the new Next 13 weeks and Week to date time frames.

How it works
Weeks follow your organization's calendar: the day your week starts and how weeks group into months. A model's timescale is set when you create it, so use Weekly for cash and short-term planning and Monthly for everything else. Your existing models stay monthly. Formulas work as usual, with t-1 meaning last week: Opening Cash = Closing Cash.t-1.

Try it now

  1. Check your week calendar in Company settings → Configuration.
  2. Create a new model and choose Weekly.
  3. Add your variables, or follow the 13-week cash flow tutorial step by step.

Available for all organizations. Full guide in the Academy.

🗂️ Create datasets with the AI Agent
3 weeks ago

🗂️ Create datasets with the AI Agent

Attach a file or pick an integration, and the AI Agent sets up the dataset for you: columns typed, dimensions mapped, data loaded.

What's new
Ask the AI Agent to create a dataset from an Excel or CSV export, or from one of your connected integrations. It proposes a type for every column, the columns to ignore and how each text column maps to your dimensions, including a new dimension when none fits.

How it works
Nothing is created until you confirm. Correct the proposal in plain language, confirm once, and the Agent creates the dataset and links you to it. Files load every row right away. For integrations, the Agent asks which months to sync once the dataset exists.

Try it now

  1. Open the AI Agent and attach an .xlsx or .csv export up to 4.5 MB.
  2. Type "Create a dataset from this file".
  3. Review the proposal and confirm.

Available to Admins and Super Admins. Full guide in the Academy.

🤖 AI Data Entry: update your Input Tables by describing your plan
3 weeks ago

🤖 AI Data Entry: update your Input Tables by describing your plan

What's new
Budgeting season just got lighter for Budget Owners. Budgeting starts with decisions, not cells, so now you can tell the Agent what's changing in your plan, and it updates your Variables in the Input Table for you.

How it works
Abacum Intelligence reads your request alongside the data already in your Input Table, including prior inputs, Actuals, and historical patterns, and works out the impact for you. Nothing changes until you approve the proposal. Once you apply it, the updates show up in the table like any other input, and your request is logged with them.

Try it now

  1. Open your Input Table, invoke Abacum Intelligence
  2. Describe your plan the way you'd explain it to your Finance partner: "Same team as last year, but the Atlassian contract goes up 15%. We're dropping ChatGPT. Adding Claude at €50k starting Q2."
  3. Abacum turns that into a proposal: which values change, which new rows are added, and what amounts go where, based on your existing data.

Available to all users. Link to Academy available soon.

🚀 Meet the AI Modeler: describe your model, get it built
4 weeks ago

🚀 Meet the AI Modeler: describe your model, get it built

Building a model used to mean knowing the syntax, or knowing the one person who does. Not anymore.

Open the AI Agent and tell it what you need:

"Create a P&L model from our GL, by Department, forecasting into FY26 Forecast"

The Agent scans your datasets and, a few minutes later, shows you a proposal: every variable with its actuals and forecast formulas. Review it, ask for changes in plain language, and click Approve. The model is built right away and opens in the model builder, planning-ready. Built on your data, calculated by the Abacum Engine, never saved without your approval.

What you can do today

  • Build any model from a prompt. P&L, Balance Sheet, Cash Flow, Headcount & Payroll, OPEX, Working Capital, ARR Bridge, Cohorts, Sales Capacity, or whatever you describe. Actuals and forecast included.
  • Grow the models you already have. Ask for a new variable or a new section in an existing model. The Agent proposes it; you approve.
  • Start from a spreadsheet. Attach a small Excel file with the structure of the model you run today, and the Agent proposes the same lines on your Abacum data.
  • Understand any model. Open a model and ask "walk me through this" or "how is Gross Margin calculated?".

Try it now

  1. Open the AI Agent.
  2. Type "Create a P&L model" or describe the model you have been putting off.
  3. Review the proposal and click Approve.

Available to Admins and Super Admins. Full guide in the Academy link. Coming next: editing existing variables and building a model from a full Excel model, formulas included.

📖 Who changed what, and when. Every model edit on the record
a month ago

📖 Who changed what, and when. Every model edit on the record

Numbers and model structure change, and it isn't always clear why. A formula was edited, a variable's setting changed, a model was renamed or restructured. The Activity ledger now tells you who did it, when, and what the value was before.

✨ What's new

  • The Activity ledger, which already tracked your versions, scenarios and manual inputs, now records every structural and content change to your models and variables, with the person who made it and, for most edits, the value before and after.
  • On the model side, it captures creating, duplicating, renaming, moving and deleting a model, creating, renaming and deleting the sections that organize your models, and every change to the switchover date, including the automatic moves that happen when new actuals sync in.
  • On the variable side, it captures creating, duplicating, renaming and deleting variables, formula edits per version, actuals formula changes, calculation strategy, input type, aggregation, dimensions, style, description, and importing a global variable from another model. Formula changes made at the sub-dimension level are recorded too: open View changes on the event to see the previous and new formula for each dimension item.
  • You can also just ask. Tell the AI Agent "What changed in this model last week?" or "What did Ana change in Revenue since July 1?" and it answers from the same ledger, with the same permissions, grouping everything saved together as one change.
  • Deleted models and variables keep their full history, so you can always trace back what happened to them.

⚙️ How it works

Open More (…) → Activity from the left sidebar. Each row is a single change, sorted from most to least recent, with the event, its details, the affected resource and the user who made it. The ledger is permissioned by access, so you only see events for the models you have access to.

The ledger starts recording from the moment the feature is enabled for your organization, so earlier changes are not captured.

🔜 Coming soon

  • Access from the public API.
  • Filters and download on the Activity page.
  • A richer visual format for the Agent's activity answers.

📚 Learn more in the Academy

🗺️ Meet the Model Map: see how every variable connects
a month ago

🗺️ Meet the Model Map: see how every variable connects

We got feedback that the old full-model view was too cluttered to read or present. We are moving away from the old diagram, and you can really understand what drives any number. The Model Map opens focused on a single variable and shows exactly what feeds it and what it feeds, so you can trace the logic behind an output, spot where a number comes from, and explain your model to anyone.

✨ What's new

  • A new Builder / Map switch lives at the top of every model. There are two ways in: click "Show variable in diagram" on any variable to jump straight to it, or open the Map tab and pick a variable from the structure panel. Either way, the Map centers on that variable and lays its dependencies out left to right, precedents on one side, dependents on the other.
  • A depth controller lets you set how many dependency levels to reveal upstream and downstream, independently, so you can follow a chain as deep as you need, from Units Sold to Net Income.
  • A left-side structure panel mirrors your sections, groups and variables so you can find anything in context, even variables tucked inside groups. Two more tabs list the external models connected to this one and the datasets feeding it.
  • Nodes now show each variable's location, logic type and dimensions; datasets appear as source nodes with their integration and last sync; and cross-model references render as external variables colored differently, so data lineage is clear end to end.
  • You can also read the logic behind every variable. Each node shows how it's calculated, whether that's a formula, a manual input, a moving average, an AI forecast or same-as-actuals. And for mixed-logic variables, where the calculation differs by dimension, you can now see the logic broken down per dimension, so even the most complex parts of a model are readable at a glance.

  • Right-click any node for its options:

    • "Filter by this variable" makes it the new focus of the Map, so you can pivot from one variable to the next to progressively investigate upstream or downstream dependencies.
    • "View in model builder" takes you back to the Builder with that variable selected. Selecting a node opens its info panel with description, configuration and dependencies, read-only.
  • Trace a path between two variables: click one, then another, and the Map marks the route connecting them.

📚 Learn more in the Academy

⚡ One line per item. Less to fill, less to scroll
a month ago

⚡ One line per item. Less to fill, less to scroll

The easier a space is to fill, the sooner the numbers come back to you. A vendor contract needs its active months and its cost. Until now, each of those variables took a row of its own: the same vendor repeated down the table, and the number you wanted to change buried among rows that all looked alike.

One click in the input table's setup turns on Pivot variables, and the table turns around. Items become the rows, variables become the columns. Your contributors choose the vendor once and fill in its dates, its cost, and anything else across that single line, then read the whole thing back in one go.

Learn how to set up a pivoted input table