Abacum

Data comes into Abacum through more than 700 native integrations across ERP, HRIS, CRM, billing and data warehouse systems, plus SFTP and an Excel connector, and the AI works on the model those feeds keep current. Teams that keep hybrid models in spreadsheets stay in step through a two way Google Sheets integration or Excel uploads.

The MCP connection runs the other way, carrying Abacum's governed answers out to Claude, Gemini and ChatGPT. None of the agents creates, updates or sends anything in the source systems themselves, so their actions stay inside Abacum's own models, spaces and mappings.

Sourceabacum.ai/product/dataread 2026-10-13

AI Modeler works from a plan. Asked for a model, it scans the connected datasets, picks a structure from its blueprints and proposes every variable and formula, and once approved it builds the model with its dimensions and totals in one pass, the same way it adds a variable and a new breakdown to a model that already exists. Workflow automation carries planning across people. Department spaces are duplicated by dimension, open and lock by status, and route budget and headcount requests to finance for a decision.

Sourceabacum.ai/blog/ai-modelerread 2026-10-13

Answers come from the governed model Abacum keeps current from connected systems, so a question about pipeline conversion or spend by vendor rests on the same actuals, plans and dimensions finance reports from. AI Modeler also draws on a curated library of model blueprints that Abacum keeps extending. Board packs, contracts, benchmarks or meeting notes attached to a chat add outside context to that conversation alone.

Sourceabacum.ai/watch-and-learn/how-can-i-add-context-to-abacum-intelligence-agent-conversationsread 2026-10-13

AI Modeler shows its whole proposal, variable by variable with the logic behind each, and saves nothing until a user approves it, after refining it in plain language if needed, or rejects it. A delete needs explicit confirmation, with its downstream impact shown first. The agent can read or change only what the user could already read or change by hand, and budget requests from department heads wait as pending until finance approves or rejects them.

Sourceabacum.ai/blog/ai-modelerread 2026-10-13

Single sign on works with any identity provider that uses SAML or OpenID Connect, and roles are assigned by group from one screen, down to sensitive payroll and compensation data, with the AI working inside that same permission structure. Abacum holds a SOC 2 Type II report and an ISO/IEC 27001:2022 certificate issued by Armanino LLP and declares GDPR compliance. Data is encrypted at rest with AES 256 GCM and in transit over TLS 1.2 or later, and its trust center shares reports and policies on request.

Sourceabacum.ai/product/securityread 2026-10-13

Any result the AI produces can be inspected from its cell, showing the data sources, formulas and assumptions behind it. Abacum keeps a history of every edit to models, spaces and dimension mappings, and asking the agent what changed in a forecast returns the changelog with previous and new values, the dimensions touched and the person behind each change, inside Abacum or through an assistant connected over MCP. Each department head can pull the same trail for their own changes.

Sourceabacum.ai/product/intelligenceread 2026-10-13

Within a conversation the agent keeps what it has been given, so a question asked again after a board pack is attached comes back with the pack's drivers folded into the answer. Approved models, published spaces and budget changes persist as the planning data itself. There is no sign of a memory that follows a user from one chat to the next or holds a team's conventions for later questions.

Sourceabacum.ai/watch-and-learn/how-can-i-add-context-to-abacum-intelligence-agent-conversationsread 2026-10-13

Every customer runs on Abacum's AWS environment in the European Economic Area, in Ireland and Germany, with no other region on offer. AI processing on AWS stays inside the EEA, Microsoft's AI services run in the EEA and Anthropic in the United States. Abacum's data processing terms place the primary processing in the European Union and allow transfers to the United States where the service needs them. A buyer that must keep data in its own country or cloud has no option to choose.

Sourcetrust.abacum.ai/subprocessorsread 2026-10-13

AI Modeler can start from a curated library of model blueprints, so a requested P&L or headcount plan follows a proven structure from the first build. AI Spaces comes with a library of finance templates, ready prompts that build the reports finance runs each month on the customer's own model in a click. The AI Classifier, anomaly detection, AI Forecasting with backsolving and Modeler each do a separate job and work without the others.

Sourceabacum.ai/product/intelligenceread 2026-10-13

Incoming data starts work without anyone asking. As actuals land from connected systems, the AI classifies new accounts, maps and cleans the records and flags anomalies as they appear, and it pulls in business signals such as deal sentiment and product usage. Modeler and the chat agent start from a person's request inside Abacum, by typing or by voice, and the MCP connection lets the same question start in Claude, Gemini or ChatGPT.

Sourceabacum.ai/newsroom/abacum-rethinks-ai-for-finance-with-the-launch-of-abacum-intelligence-a-platform-wide-intelligence-layerread 2026-10-13

Abacum picks the models. Its AI features run through AWS inside the EEA, Microsoft's Azure AI services in the EEA and Anthropic in the United States, and no setting lets a customer choose or swap the model behind an agent. Calculations never go to a model, since Abacum's own engine performs every one. A team that prefers its own assistant can reach Abacum data from Claude, Gemini or ChatGPT, while the agents inside Abacum stay on Abacum's choice.

Sourcetrust.abacum.ai/subprocessorsread 2026-10-13

An MCP connection lets Claude, Gemini and ChatGPT query Abacum data under the same governance and pull the forecast change report. Its address, sign in method and tool list are not public, and no public API or developer reference for the platform is offered, so outside software works with Abacum through that connection, the Excel connector, SFTP and exports.

Sourceabacum.ai/product/intelligenceread 2026-10-13

Nothing lets a customer test an agent before it reaches users, such as scored test cases or a staging step for AI changes. AI Modeler's Review mode reads a customer's model and suggests where its logic can be simplified, which checks the model, not the agent. Abacum runs its own observability and evaluation tooling for the language models behind its features, out of the customer's hands.

Sourceabacum.ai/blog/ai-modelerread 2026-10-13

Abacum's agents work through the platform's own model, its native integrations and its MCP connection, and none of them drives a browser or a desktop application. Data arrives through connectors and SFTP, and spreadsheets link through the Excel connector, with no screen automation involved.

Sourceabacum.ai/product/dataread 2026-10-13