Futura AI
it

Projects

Every project follows the same logic: problem, analysis, solution, architecture, implementation, results and ROI.

Except where marked with the "Verified project" badge, these are illustrative scenarios built on real use cases from the sectors we work in and do not refer to a specific client. Named case studies will be published after project completion and the relevant approvals.

Public Administration

Automating application processing in a public body

A mid-sized public body receives thousands of requests and applications every month in paper, PDF or PEC format. Each case requires manual completeness checks, requirement verification, protocol registration and preparation of a summary for the officer: long handling times, growing backlog and strong dependence on individual operator experience.

Analysis

End-to-end mapping of the case-processing workflow, analysis of document types, identification of repetitive steps and definition of where AI can support without replacing administrative responsibility. Ambiguous cases, exceptions and thresholds for human review are also identified.

Solution

A Document Intelligence system that classifies incoming cases, extracts relevant data, flags missing documents, prepares a structured summary for the operator and links every piece of information to its source. The assistant does not decide the outcome: it accelerates checking, reading and case preparation.

Architecture

OCR and document classification, data extraction pipeline, internal knowledge base with regulations and procedures, integration with protocol and document repositories, audit trail for consulted sources and on-premise or hybrid deployment to meet security and data-residency constraints.

Implementation

Rolled out in two phases: first on a low-risk case type, then progressively extended after validation with operators. Training covers system limits, exception handling and procedures for correcting or confirming extracted information.

Results

  • Reduced average pre-processing and document-check time
  • Fewer completeness errors detected in later phases of the procedure
  • More consistent summaries prepared for case officers
  • Staff freed from repetitive checks to focus on higher-responsibility work

ROI: ROI is measured through recovered operating hours, backlog reduction, lower rework and improved response times perceived by citizens and businesses.

Regional Governments

Population and business digital twin for public-policy evaluation

A regional government needs to evaluate ex ante the effects of tax, welfare or macroeconomic-shock response measures on local households and businesses, but only has static, linear macro and micro multipliers: aggregate estimates that miss redistributive, employment and financial-risk effects at the level of individual households or firms.

Analysis

Inventory of the region’s data assets (registries, tax data, business-registry records, cyclical and demographic indicators), assessment of available computing capacity, and definition of the priority policy questions to simulate, from a multidimensional view of profitability, financial soundness and well-being.

Solution

Building a population and business digital twin through dedicated micro-simulation models that replicate the region's households and firms, to simulate ex ante the effects of tax-benefit measures and macroeconomic shocks, with a multi-year time horizon and breakdowns by geographic area and sector.

Architecture

Micro-simulation models for households and businesses, integration with regional data lakes and statistical registries, high-performance computing infrastructure for running scenarios, summary dashboards for decision-makers, and versioning/audit of simulated scenarios.

Implementation

Rollout on an initial set of regional policies, validation of results with the decision-makers involved, calibration of the models on historical data, and subsequent extension to other measures, sectors and areas of the region.

Results

  • Ex-ante comparison of alternative policy scenarios before implementation
  • Disaggregated view of redistributive, employment and financial-risk effects
  • Greater transparency in evaluating the impact of public spending
  • Shared analytical basis for technical offices and policy-makers

ROI: Value is measured in policies better calibrated to their objectives, lower risk of measures with unintended effects, and reduced time needed to evaluate alternative scenarios before deciding.

Public reference: Amartya, the population and business digital twin developed by the Emilia-Romagna region with the Universities of Bologna and Modena-Reggio Emilia to simulate the effects of tax and welfare policies. This is not a project delivered by Futura AI: we cite it as a public example of this type of approach. margherita.regione.emilia-romagna.it/it/amartya

Finance

Semantic search over regulatory and compliance documentation

A banking or insurance group manages a growing volume of internal regulations, circulars, policies, procedures and compliance documentation distributed across multiple archives. Staff spend time locating correct information, and the risk is not only operational: outdated answers can create inconsistencies in controls.

Analysis

Inventory of existing document sources, assessment of quality, freshness and data structure, and definition of priority use cases: internal regulatory search, KYC/AML support, document due diligence and consistency checks across policies.

Solution

A RAG-based Enterprise Search platform, with source citation for every answer, version control and a language model adapted to regulatory, banking and insurance terminology. Answers are designed to support the team, not replace the responsibility of the compliance function.

Architecture

Vector Database for semantic search, Knowledge Graph to link related regulations, function-level permission management, query logs and hybrid deployment to meet data residency, security and audit requirements.

Implementation

Pilot phase with a single compliance team, structured feedback collection, creation of an evaluation question set and subsequent rollout to other departments after validating accuracy, sources and behavior on ambiguous cases.

Results

  • Reduced time spent on document and regulatory search
  • Greater consistency in the answers provided by the compliance team
  • Full traceability of the sources cited in every answer
  • Lower risk of using obsolete versions or non-aligned interpretations

ROI: ROI is read as fewer person-hours spent on manual search, less rework and lower operational risk tied to incomplete or outdated interpretations.

Industry

A technical documentation assistant in a manufacturing setting

A manufacturing company with hundreds of manuals, bills of materials, quality procedures and maintenance documents struggles to make this knowledge quickly accessible to production, engineering and technical support teams. Critical knowledge often remains concentrated in a few experienced people.

Analysis

Mapping of existing technical archives, analysis of formats, content quality, update frequency and priority use cases: procedure search, maintenance support, manual consultation, training of new operators and technical assistance.

Solution

A Document Intelligence assistant able to answer technical questions in natural language, cite manuals and procedures, connect components and bills of materials, and contextualize answers through MES/ERP integration.

Architecture

OCR and classification of historical manuals, semantic search across the technical archive, Knowledge Graph connecting products, components and procedures, API integration with production systems already in use.

Implementation

Started with a pilot product line, validated directly with production and support staff, collected unresolved cases, progressively improved the knowledge base and extended the system to the rest of the technical catalog.

Results

  • Reduced time spent searching for technical information
  • Fewer errors during technical support and maintenance
  • Shorter training time for new operators
  • Greater continuity of technical knowledge when people or departments change

ROI: Return is measured through fewer production stoppages caused by information search, more autonomous operators, faster support and reduced dependence on tacit knowledge.

IndustryVerified project

Automated extraction of dimensions from CAD drawings and ISO conformity checks

A precision mechanical components manufacturer receives technical CAD drawings in inconsistent formats and graphic standards across clients and suppliers. Reading dimensional data, tolerances and checking conformity against the applicable ISO standards was done manually by the engineering office: slow, repetitive work exposed to transcription errors, with direct impact on quoting and quality.

Analysis

Inventory of incoming drawing types, graphic formats in use and the ISO standards relevant to each product family. Identification of the critical dimensional fields (dimensions, tolerances, finishes) and of the points where a reading error has the greatest downstream impact, in quoting and in production.

Solution

An automated CAD drawing reading pipeline based on OCR and Vision-Language models, which extracts dimensions and tolerances directly from the technical drawing and checks them against the relevant ISO standard requirements, flagging deviations and low-confidence cases for review by the engineering office.

Architecture

Vision-Language models for interpreting the technical drawing, OCR for text and tables present on the sheet, a structured knowledge base of applicable ISO standards for automated comparison, and a review interface for human confirmation of low-confidence cases.

Implementation

Started on a subset of drawings and the most frequent ISO standards, validated accuracy with the engineering office against a sample of real drawings, calibrated the system on the errors found, and progressively extended to other product families.

Results

  • 86% accuracy in automatically extracting dimensional data from CAD drawings, measured on the client's real technical drawings
  • Reduced time spent by the engineering office on manual drawing review
  • Fewer transcription errors on dimensions during quoting
  • More systematic ISO conformity checks, with uncertain cases flagged instead of missed in manual review

ROI: Value is measured in engineering hours freed from manual drawing review, faster quoting turnaround, and lower risk of non-conformities caught late in production.