Every dimension tends to accumulate items that you've stopped using, like old vendors, renamed accounts, or other leftovers from past mappings. Over time, these can pile up, crowding the lists your team selects from and slowing down your entire workspace.

Now you can clear them out in seconds. Abacum spots the items that aren't used anywhere and removes them in one pass. This means your vendor list shifts from a long, cluttered column to a concise list of the vendors you actively work with.

Faster everywhere, because lean dimensions load and calculate quicker across every table, report, and input. And safe, because it offers only genuinely unused items, and removes nothing until you say so.

Learn more about how to Clean up dimensions

Adding a table or chart to a space normally means building it by hand: the variables, the dimensions, the timeframe, the comparison. Now you can skip that and just describe what you want. Abacum Intelligence builds the block inline on your real data, and you drag it straight into any space.

✨ What's new

• Generate tables, charts, KPI cards, and input tables from a prompt, or embed an existing dataset version. 
• Open a space and the AI Agent, describe the block you want (e.g., "revenue by location for Jan to Feb 2025 vs prior year"), then review it inline and drag it into the space or click insert. Adjust it from there as you would any block.
• Point it at the right data: type @ in your prompt to reference a specific variable, version, or dimension. The more detail you give (the breakdown, the timeframe, the comparison), the closer the result.

Need a whole space rather than a single block? That's AI Spaces: describe the report you want and Abacum Intelligence builds the entire space in one go. Block generation is the same capability that powers AI Spaces and is available on its own whenever you just need one more thing.

Learn more in the Academy.

Write a short description of your company once, and the Agent factors it into every answer for everyone on your team.

• Answers judged against your reality. Ask "is our gross margin healthy?" and a B2B SaaS company sees 75% read as strong against software norms. A manufacturer sees the same number read against much thinner industry margins.
• Written once, used everywhere. An admin adds the description in the new Company context tab in your Library. Every conversation in the workspace picks it up, with nothing to configure per user.
• Free text, no forms to fill. A few lines on your business model, size, market, and what good looks like on your key metrics is enough.
• Works with your numbers, not instead of them. The Agent still answers from your model. The description tells it how to read what it finds.

How to get started:

1. Open the Library. Admins land on Company context by default.
2. Edit the card and describe your company in a few lines.
3. Ask the Agent a question that needs judgment, like whether a margin or a growth rate looks healthy.

This is the first piece of context you can give the Agent, and more ways to ground it in your business are coming.

You can now group your spaces into sections and reorder them directly from the space list, so the reports you need are easier to find.

• Create a section, give it a name, then drag spaces into it or use "Move to…".
• Reorder sections and spaces by dragging them.
• Sections are managed by admins and leave your existing sharing untouched: people only see a section if they already have access to a space inside it.

Learn more about how to organize your space list.

The Actuals until control now supports relative time presets. Pick Current month or Last month in the picker, and the space follows the calendar without touching the setting each cycle.

✨ What's new

• Two new preset options in the Actuals until picker: Current month and Previous month.
• The resolved date rolls forward as the calendar advances, without admin action.
• The header chip shows the resolved date and the preset name, e.g., "Actuals until Mar 2026 (Current month)".

⚙️ How it works 

Open the Actuals until picker, pick a preset, and click Save for everyone.

Learn more in the Academy.

The Agent can now read the context of the documents where your decisions actually live. Attach a board deck, meeting transcript, offline spreadsheet, or policy doc to any conversation, and the Agent combines it with your Abacum data to answer as your real business context partner.

✨ What's new

A lot of the "why" behind your numbers sits outside the platform: the re-forecast discussed in a board deck, the hiring pause approved in a meeting, the covenant defined in an operating plan. Now you can bring that business context straight into the conversation.

Click the new attach button (+) in the Agent input, add one or more files with your question, and the Agent uses their content alongside your models and datasets, not instead of them. Each file shows as a chip on your message and stays part of the conversation for follow-ups.

📈 Impact

• Cross-check documents against live data, attach your FY2026 board operating plan, and ask "What's the EBITDA burn covenant, how much have we burned to date, and how much headroom is left?" The Agent reads the covenant from the deck and pulls actual EBITDA from your model.
• Validate reports at a glance, attach a P&L screenshot, and ask the Agent to compare it against the P&L in your Space.
• Ground answers in your source documents, meeting transcripts, policy docs, and offline spreadsheets that become part of the Agent's context.

⚙️ How it works

Click + in the Agent input (side panel or expanded view), pick your files, and ask. Supported types: pdf, csv, xlsx, html, txt, md, and images (png, jpeg, gif, webp). Files are validated at upload, so if a file is too large or unsupported, you get a clear message upfront. You can always upload just the relevant tab or section. Attachments are scoped to their conversation only and never influence other conversations or users.

Some questions are faster to say than to type. The Agent's chat input now accepts voice.

✨ What's new

Click the mic in the chat input, ask your question out loud, and the transcript lands in the input as editable text. Review it, fix a word if you need to, and send. Nothing is sent until you decide.

Dictation understands finance language. Terms like EBITDA, CapEx, ARR, or rolling forecast are transcribed correctly, and you can speak in English, Spanish, French, or German. The language is detected automatically.

⚙️ How it works

While you speak, a live waveform confirms the Agent is listening. Confirm to insert the transcript, or cancel to keep what you had typed before. Your browser will ask for microphone permission the first time you use it. Audio is processed for transcription only and is never stored by Abacum.

The Abacum MCP now covers your full data pipeline. Your AI assistant can query the data that feeds your models, in both its raw and processed versions, and read the complete calculation logic behind any model.

✨ What's new

Your AI assistant can now see your datasets. Ask "Did last month's NetSuite data come in correctly, and how was it classified?" and it lists your datasets with their source, last sync time, and row counts, compares the raw data against the processed version, and queries either one directly. Data quality checks that used to mean digging through loads now take one question.

It can also read your model logic. Ask it to explain a model, and it sees every formula, how variables connect, and how each one aggregates. Ask it to review a model, and it can spot improvement opportunities grounded in the actual calculation logic, not guesses.

📈 Impact

• Close-day data checks — confirm a sync landed and see how it was classified, in seconds
• Model documentation — get any model explained variable by variable, on demand
• Model reviews — improvement suggestions based on the real formulas behind your numbers

⚙️ How it works

The same query engine that powers the rest of the Abacum MCP. Your data is loaded into a fast engine on our side, and the AI runs targeted queries against it, receiving only the rows it asked for. Everything stays read-only and scoped to your Abacum permissions: Super Admins see all datasets and models; Admins see only what's shared with them.

🚀 Roll-out

Live for all organizations with MCP enabled. If your AI assistant was already connected, disconnect and reconnect the Abacum connector to pick up the new tools.

Spaces now work more seamlessly on smartphones and tablets, so you can check the numbers and move a report forward from any device, anywhere. Whether a CFO is reviewing the monthly board pack between meetings or a budget owner is checking budget vs. actuals on the go, the report is always just one tap away.

✨ What's new

• Review anywhere: consume reports, KPIs, charts, and tables from any device.
• Approve on the go: change a status without opening a laptop.
• Built for stakeholders: a consumption-first experience for executives and budget owners.

⚙️ How it works

Open any Space on your smartphone or tablet, and it adapts automatically to your screen size. Navigation collapses into a menu to maximize the view, and you scroll vertically and horizontally to move through your content. No setup required.

Learn more in the Academy.

The Agent now keeps every conversation, so you can run several analyses in parallel and return to any of them with full history.

• Start fresh without losing anything. Ask AI from a space or table opens a new conversation with that context, and your previous one stays saved in the list.
• Find past work in seconds. Conversations get automatic titles and are grouped by date.
• No more waiting. Long-running tasks keep working in the background while you ask something else in a new conversation.

Learn how conversations work in the AI agent article.