What challenges did BMTax face before AI implementation?

Fragmented IT infrastructure and heavy manual processes limited scaling and slowed analysis of rapidly growing, highly regulated tax volumes amid major tax reforms. The firm needed a more unified, secure, and data-driven operating model for tax and fiscal consulting.

What was the impact of the AI solution?

The platform processes 5 million tax documents per minute. BMTax initially increased productivity by 15–25% after removing manual processes. Improved traceability reduced the number of inconsistencies employees manually reconcile by 20–35%. BMTax has analyzed more than R$2 trillion in fiscal records. The firm says the platform creates a foundation for new data- and automation-based services and better tax risk/opportunity identification.

Source

Microsoft

BMTax processes 5 million tax documents per minute with Microsoft Azure OpenAI in Foundry Models

Use case typeData platform modernizationUpdated Jun 29, 2025

BMTax is a Brazilian tax and fiscal consulting firm that was struggling with fragmented IT infrastructure and manual, knowledge-dependent processes amid major tax reforms. The company and Microsoft partner Qualiserve consolidated 45 TB of data into Microsoft Fabric in six months and built Intelligence Tax Hub, an internal platform with an Azure OpenAI in Foundry Models chatbot for natural-language data discovery and reasoning. The platform also uses Power BI and Microsoft security solutions to support analytics, governance, and sensitive-data protection.

Organization: BMTax
Industry: Finance
Location: Brazil
Published: June 2025

Reported outcomes

−35%

manual reconciliation inconsistenciesAutomation & deflection

5,000,000 documents/minutetax documents processed per minute+15%productivity+25%productivity−20%manual reconciliation inconsistencies2,000,000,000,000 BRLfiscal records analyzed

Strategic outcomes

Scale & capacityUnified tax data at enterprise scaleRisk & complianceImproved traceability for regulated tax operationsNew product / capabilityFoundation for new AI business solutionsNew business modelPlans to create data-based services for clients

Catalog median for automation & deflection deployments: −50% across 47 reported metrics. Compare benchmarks →

Primary read

Use case focus

Showing 2 of 2

1Data platform modernization
2Conversational analytics

Fragmented IT infrastructure and heavy manual processes limited scaling and slowed analysis of rapidly growing, highly regulated tax volumes amid major tax reforms.
The firm needed a more unified, secure, and data-driven operating model for tax and fiscal consulting.

BMTax worked with Microsoft partner Qualiserve to build Intelligence Tax Hub on Microsoft Fabric, unifying 45 TB of data into a centralized lakehouse within six months.
The platform includes an internal chatbot powered by Azure OpenAI in Foundry Models to help employees discover and interact with data using natural-language retrieval and reasoning.
Power BI provides analytics and visualization, while Microsoft security solutions help protect sensitive, highly regulated data.
BMTax says it is also building specialized AI agents on top of the platform for intelligent querying and scenario simulation.

Technologies

Azure OpenAI in Foundry Models Microsoft Fabric Power BI Microsoft security solutions

The platform processes 5 million tax documents per minute.
BMTax initially increased productivity by 15–25% after removing manual processes.
Improved traceability reduced the number of inconsistencies employees manually reconcile by 20–35%.
BMTax has analyzed more than R$2 trillion in fiscal records.
The firm says the platform creates a foundation for new data- and automation-based services and better tax risk/opportunity identification.

Architecture

Intelligence Tax Hub is built on Microsoft Fabric with 45 TB of data unified in a centralized data lake. Azure OpenAI in Foundry Models powers an internal chatbot that uses natural-language retrieval and reasoning. Power BI supports analytics and visualization, and Microsoft security solutions protect sensitive data. The article also notes plans for specialized AI agents for querying and scenario simulation.

Implementation partners1

Qualiserve

Sources & evidence1

Groundedness: 5/5Type: Customer StoryPublished: Jun 29, 2025Publisher: MicrosoftEvidence: PrimaryConfidence: High

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence