Lucanet

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

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

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

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

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

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

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

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

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

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

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 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

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 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