Building Leonardo's workforce strategy using the Draup MCP connector on Claude

~60000

Employees

$20B

Revenue

Aerospace & Defense

Industry

Rome, Italy

Headquarters

The Core Challenges

Role evolution framework
Leonardo had no unified framework for tracking how roles were evolving across digital engineering, avionics, and cybersecurity, which limited forward-looking skills planning.
Talent ecosystem visibility
Visibility into external digital talent ecosystems was thin, so peer benchmarking and build, buy, or borrow decisions were hard to defend.
Learning and talent hotspots
Learning investment was not tied to in-demand skills, and the company lacked a view of the software and digital twin talent hotspots it needed to support diversification and growth.
Analyst throughput
Every data pass across the Leonardo workstreams, the LDO institute study, and the talent migration analysis began with hand-written SQL, iterated by hand, typically one to two days before analysis could start.
OUTCOME
A data pass that took one to two days of hand-written SQL now happens in a single conversation
The recovered time went into synthesis and storyline, letting Draup scope and deliver a broader, more strategic Leonardo mandate faster than the narrower version used to take.

What we did

Draup delivered Leonardo's workforce strategy with the Draup MCP connector carrying Draup's data into Claude for the institute study and the talent migration analysis.

For the Leonardo institute study and the talent migration analysis, Draup's team ran the data work inside Claude. The Draup MCP connector gave Claude direct access to Draup's organization-level profile datasets. Sonnet handled the extraction and cleanup conversationally, and Sonnet and Opus grouped the profile data straight from Draup over MCP.

Before this, every data pass started with SQL written and iterated by hand, typically one to two days of analyst effort before any analysis could begin. With Draup's data reachable through the connector, extraction and cleanup now complete in a single session, and the front-end effort collapsed to a fraction of what it was.

The saved cycles went back into synthesis and storyline rather than data wrangling, so each report started from a stronger base than the last. Beyond speed, Claude's research layer widened what Draup could credibly scope: secondary research, market context, and peer benchmarking now sit alongside the Draup data, letting the team pitch sharper, more strategic mandates and still turn them around faster than the narrower version used to take.

Claude in the workflow

The Draup MCP connector puts Draup's data inside Claude. For the Leonardo institute study and the talent migration analysis, the organization-level profile data was pulled and grouped in conversation instead of through hand-written SQL.

Sonnet 4.6
Draup profiles, pulled in conversation
Organization-level profile datasets pulled directly from Draup over MCP and cleaned in the same session, replacing the SQL that was written and iterated by hand.
Replaces 1 to 2 days of hand-written SQL
Sonnet 4.6 & Opus 4.6
Draup profile data, grouped in the same session
The models grouped organization-level profile data directly from Draup over MCP, in the same conversational session as the extraction and cleanup.
Grouped in the same session
Claude research layer
Draup data plus market context
Secondary research, market context, and peer benchmarking sitting alongside the Draup data in the same workflow, widening what Draup could credibly scope.
Widens the scope of the mandate

Outcomes

Future-ready workforce framework

Leonardo established a unified, forward-looking workforce framework that identifies emerging skill clusters in areas such as quantum engineering and simulation, and benchmarks capability evolution across peer ecosystems.

Internal mobility and agility

Advanced talent matching enabled redeployment of engineers across global business units, reducing hiring cost and improving agility.

Measurable learning ROI

Learning shifted from activity-based training to measurable learning ROI.

Data-driven workforce planning

Real-time analytics gave HR and leadership the ability to forecast role evolution and align workforce planning with technology roadmaps.
Draup is the main partner for Leonardo in talent intelligence and data analytics. We are also partnering in analyzing the evolution of skills in the midterm and the long term, so we can upskill or skill our people to be always updated to the technical evolution of new technologies. Draup is also a partner in studying particular phenomena such as the employer branding, positioning of Leonardo worldwide - how our employer branding is perceived by people in different countries or in different background. And this is very helpful to us to try to make Leonardo the best employer choice we can.
Vincenzo Cozzolino
SVP Learning & People Development, Leonardo
6,100+​
Locations
4M+​
Career Paths​
1.7M+​
Peer Group Companies​
28K+
Skills
3,500+​
Roles
1B+​
Professionals​
55K+​
Universities​
1B+​
Job Descriptions​
200K+​
Courses​
180K+​
Technology Solutions​
1.6M+​
Account Priorities​
Labor Market Data Contextualized with Business Intelligence for Every Decision

Analyzing 1B+ data points
daily from 100K+ sources

6,100+​
Locations
4M+​
Career Paths​
1.7M+​
Peer Group Companies​
28K+
Skills
3,500+​
Roles
1B+​
Professionals​
55K+​
Universities​
1B+​
Job Descriptions​
200K+​
Courses​
180K+​
Technology Solutions​
1.6M+​
Account Priorities​
SOC 2
GDPR
CCPA
ISO 27001
ISO 42001
EAIGG

Ethical AI, Backed by Global Standards

Draup, an AI-first company, upholds global standards like SOC 2, GDPR, CCPA, ISO 27001, and ISO 42001. As an EAIGG member, we audit for bias and build trustworthy AI.

Data Trust &
Methodology
at Draup

Draup uses a structured methodology to reduce inaccuracies and prevent misleading information, with a focus on transparency and responsible data practices.

Data Transparency and Coverage

Draup sources data from diverse, vetted global inputs including public datasets, labor information, professional ecosystems, and industry research. Coverage varies by region and role, and we supplement limited areas with alternative sources and analyst-led modeling.

Profiles Behind the Numbers

All aggregate insights related to buyers, roles, skills, and locations are grounded in structured, anonymized human and organizational profiles rather than pure extrapolation. This ensures context, reliability, and protection of personal identities.

Data Hygiene and Integrity

We maintain a clean, accurate data environment by removing duplicates, outdated entities, and invalid records. Automated checks powered by ML models and analyst reviews work together to ensure clarity and accuracy for every entity, such as buyer, role, skill, technology, or company.

AI Governance and Bias Mitigation

Our governance framework combines automated evaluations with Human-in-the-Loop reviews. We use statistical checks, audits, and cross-source comparisons to reduce demographic and structural bias before insights reach the platform.

Compensation Guardrails

Compensation insights use blended, directional inputs such as aggregated ranges, benchmarks, modeled distributions, and market signals. We distinguish clearly between modeled and reported data and apply guardrails to prevent over-interpretation.

Hourly and Frontline Workforce Coverage

For hourly, frontline, and blue-collar roles where digital visibility is limited, we incorporate government datasets, localized labor information, and specialized partners to build a more complete and balanced view of workforce supply and demand.

Draup Logo
Ⓒ 2026 Draup. All Rights Reserved.
SitemapLlms.txt