Datarails

FinanceOS connects to more than 600 systems and data sources, from ERPs, CRMs and HR platforms to banks, billing systems and spreadsheets, and keeps them synchronized and consolidated. The AI works on what arrives. Spend codes, matches and reconciles invoices and card transactions against ERP entries, Desk pulls invoice, payment, vendor and customer records into each request, and the assistant drafts a journal entry in the conversation for a person to check and post. Corrections and payments stay inside Datarails, and no agent posts a change back into the ERP or CRM by itself.

Sourcedatarails.com/platform/financeosread 2026-10-13

The strategy, planning and reporting agents have merged into one general assistant, which asks clarifying questions, offers analysis options, confirms the key decisions and then builds the output, so one request can run from a data pull to a finished Excel model and deck.

Task agents sit inside the screens where the work happens, such as flux analysis and journal entries in the close. Workflows route budgets, forecasts and reports through the right reviewers, Month-End Close assigns tasks with deadlines across the close, and Desk routes each finance request by team, type and priority with SLA timers.

Sourcesupport.datarails.com/hc/en-us/articles/25257415989916-introduction-to-datarails-ai-agentsread 2026-10-13

Agents work on FinanceOS, a governed data model that consolidates, maps and harmonizes data across entities, currencies and systems, with mappings, allocations and version control kept by the finance team. A Semantic Layer defines business metrics such as revenue, gross margin, headcount, ARR and DSO once for use across Datarails, and the assistant says whether a number came from a governed metric or an aggregation of the tables. Every answer can drill from a summary to departments, accounts and transactions.

Sourcedatarails.com/platform/financeosread 2026-10-13

Before creating or changing anything, the assistant states exactly what will change and waits for the user's OK, so nothing is created or changed without approval. A journal entry arrives in the conversation as a draft for the user to check, and a person posts it, never the agent. In Spend, agents work under defined controls and approval requirements, so a person approves before any payment, and invoices with discrepancies wait for review. Desk drafts each reply for a team member to review and send.

Sourcesupport.datarails.com/hc/en-us/articles/30100850412444-using-the-datarails-ai-assistant-betaread 2026-10-13

Datarails holds a SOC 2 Type II report and a SOC 1 report, both available on request from its trust center. Sign in supports SAML 2.0 single sign on with Okta, Microsoft Azure, Duo, Google Workspace and JumpCloud, with multifactor authentication. Access follows roles (Super Admin, Admin, Contributor and Viewer) and permission groups down to the entity, department or report, the AI tools read only what the user is already allowed to see, and authorization is checked again on every request.

Sourcetrust.datarails.comread 2026-10-13

FinanceOS keeps audit trails and full data lineage on the numbers, and the close records approvals and every change. Super Admins get an audit log of outside assistant sessions on the AI Connector, listing each session's member, AI platform, time, duration and status with a timeline of its events, while a durable record of each tool call is still being built. Conversations with the in app assistant stay visible only to the user who had them, so an admin has no record of an agent session to open later.

Sourcedatarails.com/platform/financeosread 2026-10-13

Every conversation with the assistant is saved automatically for the user who had it, across all areas of the product, and nobody else sees it. Each conversation runs as a session on Anthropic's infrastructure, which holds its history, files and outputs, so it falls outside Anthropic's zero data retention option. A team can also keep company profile documents, such as board presentations or financial models, that agents and outside assistants read for context, and the team reviews and updates them itself. An agent does not write down what it learned from a conversation for next time.

Sourcesupport.datarails.com/hc/en-us/articles/25257473410332-how-ai-agents-use-context-metrics-and-dataread 2026-10-13

Datarails runs on Microsoft Azure in the United States, Canada and the UK, and each customer's environment sits in one of those regions, with the application database following the same Azure location. When a user works with the assistant, some data leaves Datarails for Anthropic's infrastructure, in a region left unnamed. The AI Connector is processed in the United States, with routing by region under evaluation and no delivery date. The platform is a hosted service with no customer hosted edition.

Sourcedatarails.com/sub-processorsread 2026-10-13

Agents sit ready in the screens where finance work happens, each switched on for an account separately: flux analysis and journal entry drafting in the close, a month end close assistant, cash transaction matching and an intercompany reconciliation assistant. Spend adds agents for invoice extraction and coding, transaction classification, matching and exception checks, and Desk adds an assistant that drafts answers to finance requests. Teams working in Claude get a Datarails plugin with ready made finance skills that produce Excel workbooks and PowerPoint decks.

Sourcesupport.datarails.com/hc/en-us/articles/30100850412444-using-the-datarails-ai-assistant-betaread 2026-10-13

Insights sends AI written summaries on the schedule a team sets, weekly, monthly or quarterly, to the people it chooses, and automated agents rerun recurring analyses without being asked. Desk takes finance requests from email, Slack, Teams and other channels into one queue, where the AI gathers the records and drafts an answer. People also reach the agents and the assistant in the web app, and outside assistants reach the data through the AI Connector.

Sourcedatarails.com/platform/airead 2026-10-13

The assistant and the agents built into Datarails screens run on Anthropic's Claude models through Anthropic's Claude Managed Agents platform, and other AI features use OpenAI models, directly and through Azure OpenAI. A customer cannot switch its agents to another provider or model. Teams that prefer Claude or ChatGPT can also query Datarails data through the AI Connector, but that is their own assistant reading Datarails.

Sourcesupport.datarails.com/hc/en-us/articles/30100850412444-using-the-datarails-ai-assistant-betaread 2026-10-13

The FinanceOS AI Connector is a hosted MCP server with OAuth 2.0 and PKCE sign in per user and a public tool list for discovering tables, reading metrics, running filtered queries and aggregations. Every connector tool is read only for now, so an outside agent can analyze Datarails data but not change it. Any Datarails customer can also pull its tables over an OData feed at no extra cost, and the Data Gateway Service API accepts CSV and Excel uploads into Fileboxes from other systems.

Sourcesupport.datarails.com/hc/en-us/articles/25849710214556-datarails-financeos-mcp-server-technical-documentationread 2026-10-13

Custom AI workflows built under the AI Transformation package are tested against real data by a Datarails forward deployed engineer before they go live, which is a service, not something a team runs itself. Datarails' AI terms leave it to the customer to review outputs for accuracy before relying on them, and within the product a finance team cannot score an agent's answers or try it on known questions before rolling it out.

Sourcedatarails.com/datarails-ai-transformation-servicesread 2026-10-13

Agents work on FinanceOS data and produce Excel files, decks, PDFs and widgets inside Datarails. Data from other systems arrives through connectors and uploads, and when Claude works in Excel the Datarails add in carries out refreshes and drill downs rather than an agent reading the screen. None of Datarails' agents operates another application's screen for a user.

Sourcedatarails.com/platform/airead 2026-10-13