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.

Abacum has a fresh look. We've redesigned the platform's layout to give your data more room and make every page feel familiar.

✨ What's new

Spaces, Models, Datasets, and Dimensions now share one consistent structure, so wherever you work, everything is where you expect it to be. A new top bar keeps the essentials at hand, and a right-side drawer lets you check any resource's details and activity without opening it.

Abacum Intelligence gets a better home too: the Agent now sits in a side panel next to your content, so you can ask questions and keep working on your Space or model at the same time.

🚀 Roll-out

We're gradually rolling out the new layout over the next few days. Want it sooner? Reach out to your CS contact and we'll enable it for you.

Academy articles will be updated progressively to reflect the new layout.

Finding the right variable in the Library is now faster than ever. The top bar has new filters that let you narrow a long list down to exactly what you need.

⚡What's new

You can now filter your variables directly from the top bar of the Library. Click + Add filter and choose to filter by Variable, Model, or Active dimension, then pick the values you care about. The list updates instantly, so you can jump straight to the variables behind a specific model or dimension.

Each filter appears as a chip you can edit or remove at any time, and you can stack several filters together to zero in on precisely the variables you want to work with.

⚙️ How it works

Filters combine with AND logic, so a variable is shown only when it matches every active filter. For example, filtering by Model = Revenue and Active dimension = Region returns just the variables that live in the Revenue model and use the Region dimension. 

One month for the whole space, in one click. The new Actuals until control anchors every table, chart and KPI card in a space to the month you pick. By default, each block resolves to its own switchover date, so a single space can silently show several "current months" at once. Actuals until overrides that behaviour, allowing you to align all to the same month!

What's new:

• Cap actuals across the space: actuals stop at the selected month. Columns beyond it show empty unless the block has an estimate, in which case the version takes over from there.
• Anchor relative timeframes: MTD, QTD, YTD and similar resolve to the selected month, on every block including those with no actuals.
• Let members explore: admins can enable Actuals until for members. Members can then adjust the month for their own session without changing the saved view for others.

How it works:

Open the Filters and Controls panel in any space, add the Actuals until control, pick a month, and click Save for everyone. The space header shows Actuals until [Month Year], and every block anchors to the selected month.

Learn more in the Academy.

Setting up a space from scratch means configuring every KPI card, table and chart by hand. AI Spaces lets you beat the blank canvas: describe what you need and Abacum Intelligence builds the whole space for you, populated with real data and styled with your company colors, delivering a solid first version from just one prompt. 

✨ What's new

• Describe the report you want in plain language, or start from a pre-saved template (Financial Reporting, Headcount Planning, OPEX Reporting or Revenue Operations). 
• Abacum Intelligence assembles KPI cards, tables, charts and text blocks into a complete, laid-out space, and everything stays fully editable, just like a space you built by hand, so you keep full control. Magic 🪄 
• The more detail you give, the better the result. 

→ What’s next? Plan mode is coming soon, where Abacum Intelligence shares an outline of the proposed space to check and refine via chat. Watch this space!

⚙️ How it works

• Create a new Space and choose Generate with AI.
• Type a prompt describing the report, or pick a template and tweak it, then click Generate. 
• Generation runs in the background, so you can keep working while it builds. Available to Admins and Super Admins.

Learn more about AI Spaces in the academy. 

You can now ask the Abacum Intelligence Agent for the full history of changes to your manual inputs: who changed a value, when, what it was before and after, and more.

• Ask in plain language. For example, "List all the changes made in 'Inputs budget 2027' input table in the last 30 days", then follow up to narrow the results by person ("only the ones from Daniel"), variable ("only OPEX"), dimension item ("only the Product department"), and more.
• Go straight to the source of a change. Instead of comparing versions by hand or asking around, have the Agent trace a specific movement back to the exact edit behind it, for example "Did someone change the Claude vendor expense in the Budget 2027 version?".
• Everyone sees what they should. Super admins can access all changes, while admins and members can access their own.

Learn more about how to track changes to your inputs.