Cube vs Lucanet (2026)

Cube connects to hundreds of source systems, with guides for NetSuite, Salesforce, Workday, Sage Intacct, Snowflake, Databricks, ADP Workforce Now, QuickBooks, HubSpot, Rillet, Dynamics 365 Business Central and Campfire, and syncs them on a schedule or on demand. Agents can start a fresh import from an existing connection before they answer, and they put their work into Cube scenarios, Boards, Tables and decks. None of them books an entry, updates a deal or changes an employee record back in the ERP, CRM or HR system.

Sourcecubesoftware.com/integrationsread 2026-10-13

More than 300 standard interfaces to ERP and accounting systems, a flexible Excel interface and direct access from third party systems bring data into the CFO Solution Platform, and xP&A also connects to accounting, CRM, HRIS, payroll and BI sources or takes data pushed by webhook. The workflow agents act on what lands there. They build models in xP&A, tag filings in XBRL Tagger, map emissions in ESG Reporting and reassign roles in Disclosure Management, and none of them writes back into the ERP or the other systems the data came from.

Sourcelucanet.com/en/platform/integrationsread 2026-10-13

Charlie, the super agent, breaks a question into tasks, routes each piece to one of four agent teams (Data Managers, Analysts, Planners and Business Partners), lets them pull, reconcile, model and draft, then checks the combined answer against the source data before returning it. One request can run from a data refresh through variance analysis to a drafted board deck. Cube Workflows add task lists with owners, assignees, statuses and due dates for processes such as the month end close.

Sourcecubesoftware.com/ai-agentsread 2026-10-13

Lume takes a request in plain language and routes it to the agent built for that job, and Lucanet's most advanced workflow agents run ten to thirty steps or more, interpreting the request, forming a plan, querying data and calling tools in sequence.

The Modeler Agent proposes a whole build plan of sections, variable groups, variables, timesteps, aggregations and formulas, then builds the model in one pass once the user approves it.

Outside the agents, Consolidation & Financial Planning workflows run scripts, data imports and apps one after another in a set order, with a chosen behavior when a step fails.

Sourcelucanet.com/en/insights/ai-innovation/intelligence-inside-7-new-family-of-agentsread 2026-10-13

People reach Charlie in the Cube Workspace, in the Excel and Google Sheets add ins, in Slack and Teams, and from any MCP assistant such as Claude or ChatGPT. Anomaly Detection watches the numbers and flags lines that look off before anyone asks. Source systems sync on a schedule, so fresh actuals land in the model and the plans update around them without someone starting the work.

Sourcecubesoftware.com/ai-agents/analystsread 2026-10-13

Every agent run starts with a person. A user asks Lume or opens an agent from the Agents panel, chooses Generate a model in xP&A, runs AI tagging on a page or table in XBRL Tagger, or imports consumption spreadsheets for the ESG Emission Agent. Webhooks and the source adapters keep data flowing in on their own, but no event, schedule or inbound message sets an agent going. Lume sends a browser notification when a chat finishes, which tells the user a long request is done.

Sourcesupport.lucanet.com/en/documentation/lume/agentsread 2026-10-13

Charlie answers from the customer's own Cube. It decides which slices of actuals, budgets, forecasts and scenarios it needs and fetches them through the governed layer, with the company's formulas, account and entity hierarchies and currency conversions already applied, so revenue means what the company means by revenue. It can drill from a summary figure to transaction lines in the connected source systems, and every number opens back to the records behind it.

Sourcehelp.cubesoftware.com/hc/en-us/articles/36376094163092-about-ai-at-cuberead 2026-10-13

The agents work from one data platform that unifies ledgers, plans and subsidiaries through more than 300 source adapters, with a semantic layer that captures what each figure means in the business. The Analyst Agent builds its own data model of a user's consolidation and xP&A structures the first time that user asks a question each day, which can take up to 15 minutes, scopes it to the user's permissions and reuses it for the rest of the day. Lume answers product questions from Lucanet's knowledge base, and every output links back to its source data.

Sourcesupport.lucanet.com/en/documentation/lume/agents/analyst-agentread 2026-10-13

Each conversation with Charlie and each Planner session is saved for the user who started it, and a History view reopens any of them to carry on where it left off. Context stays inside one conversation, so starting a new one for an unrelated question keeps the earlier context from carrying over. Admins can also write standing instructions for Charlie, such as always showing budget against actuals or how the fiscal calendar runs, which apply in every conversation for every user. Nothing an agent learns in one conversation reaches the next.

Sourcehelp.cubesoftware.com/hc/en-us/articles/41283352702356-chat-with-charlie-cube-s-ai-analystread 2026-10-13

The Analyst Agent keeps memories, facts a user states such as a color palette for decks, a writing style guide or how to handle currency, and draws on them in later conversations. Asked to remember something, it offers to save it, and users can add, edit or delete entries in a Memories panel, clear them all, or switch off memory collection. Entries are private to each user and stay until someone deletes them. Lume keeps every conversation as a searchable thread for up to 30 days, then deletes it.

Sourcesupport.lucanet.com/en/documentation/lume/agents/analyst-agent/personalizing-with-memoriesread 2026-10-13

Agent writes land only in scenarios opened for AI write back or created by the AI, so the live budget stays untouched unless someone opens it, and each write carries the user's name and an AI flag. Writing through MCP needs its own permission, which only Finance or Admin users can hold, new workflows and tasks arrive as drafts with no assignee, and a publish can be undone. Data Manager agents score each proposed mapping or bulk change by confidence, and the team approves it before anything lands.

Sourcehelp.cubesoftware.com/hc/en-us/articles/54111068392724-what-ai-tools-can-do-through-the-cube-mcp-serverread 2026-10-13

The agents propose and people decide. The Modeler Agent shows its build plan, takes questions and changes, and creates nothing until the user clicks Build model. In Disclosure Management, Lume previews a transfer of document and chapter roles and applies it only after the user confirms.

After AI tagging of a Word report, XBRL Tagger opens a review window to approve or reject each suggested tag, though tags suggested on a PDF go straight in. The ESG Emission Agent puts a confidence score on every mapping with full override, and a License Manager can switch every AI feature off for the tenant in one step.

Sourcesupport.lucanet.com/en/documentation/xp-a---extended-planning-and-analysis/creating-modelread 2026-10-13

Cube holds SOC 2 Type II and SOC 1 reports, the SOC 2 examined by Dansa D'Arata Soucia, and handles data to HIPAA requirements. Sign in runs through SAML or OIDC single sign on with Okta, Duo, Google or Microsoft Entra, which an admin can enforce, plus app or text based multifactor authentication. Role based access and each user's Data Access Scope reach down to the cell, the agents inherit the asker's permissions, and separate permissions govern Charlie, the Planner, MCP read, MCP write and AI administration, so AI can be switched on or off for each use through the same roles.

Sourcecubesoftware.com/securityread 2026-10-13

Sign in can run through the customer's own identity provider over SAML or OpenID Connect, with Microsoft Entra ID, Okta or a custom provider, and multifactor authentication protects platform accounts. Administrators hand out Administrator and License Manager roles for the platform and separate roles inside each solution, and the Analyst Agent reaches only data its user may see. API tokens carry read or write scopes, belong to one user and tenant and can expire or be revoked. Lucanet holds ISO 27001:2022, ISO 27017 and ISO 27018 certificates and SOC 1 Type 2 and SOC 2 Type 2 reports for 2025.

Sourcetrust.lucanet.comread 2026-10-13

Every agent query, answer and publish is recorded with the user, the permission scope applied and the sources used, and denied actions are recorded too. The audit trail shows each data change with who made it, the event type, the number of values changed and the before and after figures, and change history marks which changes came from AI. Because answers open to the transactions behind each figure, a reviewer can see exactly what an agent relied on.

Sourcecubesoftware.com/securityread 2026-10-13

While an agent works, Lume shows the activity steps it takes, and those steps come back when a user reopens the chat later. Lucanet logs every agent action and links each output to its source data through an audit trail. xP&A keeps an audit log per model of who changed which variables, dimensions, visuals or data and when, Consolidation & Financial Planning keeps a change log, and anything done with an API token is attributed to the user who created it. Users can also rate each Analyst Agent answer.

Sourcesupport.lucanet.com/en/whats-new/whats-new-lumeread 2026-10-13

Cube runs as a hosted service on AWS, with all data and infrastructure in US based regions, and offers a data processing agreement for GDPR needs. A company that needs its financial data held in the EU or another country cannot get that, and there is no customer hosted edition.

Sourcesecurity.cubesoftware.com/faqread 2026-10-13

Lucanet hosts the platform on AWS in the EU for European customers, the US for North American customers and Singapore for ASEAN customers, and customer data stays in the one geolocation set in the contract. Lume's language model processing generally happens inside the EU, or in the customer's hosting region for some customers outside it, and the model providers keep none of the data. Chats and logs stay in the customer's AWS region, while some anonymized monitoring data can leave it.

Sourcetrust.lucanet.comread 2026-10-13

Four agent teams come with every plan. Data Managers handle mapping, bulk edits, connection setup and hierarchy upkeep, and Analysts bring slices, Smart Variance and Anomaly Detection. Planners carry the Planner Agent, Smart Forecaster and Formula Modeler, and Business Partners carry Visualization, Board Builder and Deck Builder. The Agent Exchange adds ready plays, such as a variance bridge to budget, a rolling forecast refresh, an investor update or a new entity mapping, which Charlie runs once the user fills in the bracketed inputs.

Sourcecubesoftware.com/ai-agentsread 2026-10-13

Each workflow agent arrives ready for one job. The Modeler Agent builds xP&A planning models from a description, the Analyst Agent answers questions on consolidation and planning data with narratives, charts and files, the Tagger Agent tags IFRS XBRL elements in annual reports, and the ESG Emission Agent maps consumption data to emission factors across scopes 1, 2 and 3. xP&A adds wizards for a P&L and runway model, a full P&L and balance sheet report, a headcount plan and a sales and pipeline report. A Close Agent and a Report Agent are still to come.

Sourcesupport.lucanet.com/en/documentation/lume/agentsread 2026-10-13

Charlie and the agent teams run on language models from providers available through Amazon Bedrock, chosen by Cube, with Anthropic named among Cube's subprocessors since March 2026, and Cube trains no models of its own for these features. AI settings hold a company's standing instructions and nothing else, so a company cannot pick the model behind its agents. Outside assistants such as Claude or ChatGPT can work on Cube data through the MCP server, but those are the customer's own tools reading Cube.

Sourcesecurity.cubesoftware.com/faqread 2026-10-13

Lucanet selects the models. Lume and the agents send prompts to language models hosted with Microsoft Azure, AWS Bedrock and Google Vertex AI, with no customer choice among them, and customer data is not used to train them. Binding financial calculations under accounting, filing, sustainability and tax rules stay in the platform's own deterministic engines, with the models doing interpretation, formulation and automation.

Sourcesupport.lucanet.com/en/faqs/lucanet-lumeread 2026-10-13

The Cube MCP Server, generally available on every plan with usage limits, signs users in with OAuth and offers a full tool set, from get_financial_slice_of_data and get_drilldown_data to publish_data, duplicate_scenario, create_dashboard, create_planning_table, create_workflow and initiate_import, so a team can point any agent framework at the governed model and write plans, Boards, Tables, scenarios and workflows back under the user's permissions. The Cube REST API has a public OpenAPI reference covering agent chat and Planner sessions, AI settings and credits, canvases, workflow runs and connection syncs, authenticates through OAuth with a PKCE flow, and is sold as an add on.

Sourcehelp.cubesoftware.com/hc/en-us/articles/54111068392724-what-ai-tools-can-do-through-the-cube-mcp-serverread 2026-10-13

The Platform API lets a customer's own systems work with the CFO Solution Platform without an interactive login, typically to create, update or deactivate users from a central identity system. Tokens carry read, write or read and write scopes, are tied to a user and tenant, can expire, and up to 25 can exist at a time, while the reference for endpoints, scopes and example requests sits inside the product for customers. Tax Compliance & Reporting adds a REST import API with an open reference, and xP&A accepts data pushed by webhook.

Sourcesupport.lucanet.com/en/documentation/administration/user-management/api-token-managementread 2026-10-13

Before Charlie returns an answer it checks each figure against the source data, and every query, answer and AI write sits in the log for review afterward. The Planner, still in open beta, asks clarifying questions before it builds a scenario. Cube tested its own accuracy on its own books and does not warrant AI output, reminding users on every AI surface to check results. A finance team cannot run an agent against a set of known questions to see how it does before giving it to the wider team.

Sourcecubesoftware.com/ai-agentsread 2026-10-13

Users rate the Analyst Agent's answers, and Lucanet builds its agents with evaluation first engineering and a quality flywheel that improves them release after release. That testing is Lucanet's own work. A customer gets no test cases, scores or staging step for checking an agent's output, beyond reviewing each plan or suggestion as it arrives.

Sourcelucanet.com/en/platform/artificial-intelligenceread 2026-10-13

The agents work through Cube's governed data layer, its source connections and the spreadsheet, Slack, Teams and MCP surfaces. None of them opens another application and clicks through it for a user.

Sourcecubesoftware.com/ai-agentsread 2026-10-13

The agents work through the platform's own data, models and calculation engines, and Lume reaches them through its chat panel. None of them drives a browser or a desktop application.

Sourcelucanet.com/en/platform/artificial-intelligenceread 2026-10-13