TalentGuard Brings WorkforceGPT Workforce Intelligence to Claude and Other AI Agents Through MCP

New WorkforceGPT connector gives HR teams and business leaders direct access to governed role, skills, proficiency and readiness data from the AI tools where work is increasingly getting done

AUSTIN, Texas — September 21, 2026 — TalentGuard today announced the availability of WorkforceGPT through the Model Context Protocol (MCP), bringing its workforce intelligence engine directly into Claude and other MCP-compatible AI agents.

WorkforceGPT is now available through Claude’s Connectors Directory, enabling authorized users to access TalentGuard’s role intelligence from within Claude. Organizations can also connect other MCP-compatible agents directly to WorkforceGPT.

The launch addresses a growing challenge for HR organizations: as generative AI becomes embedded in everyday work, companies can generate job descriptions, skills lists and other workforce content faster than ever. But speed alone does not make that information consistent, governed or suitable for decisions about people. AI can write a job description. WorkforceGPT builds the workforce intelligence behind the job.

WorkforceGPT creates the structured role architecture talent decisions depend on: job descriptions, responsibilities, required skills, defined proficiency levels, target proficiency expectations by role, and aligned learning resources. WorkforceGPT is designed to provide that missing intelligence layer.

Instead of asking a general-purpose AI model to infer what a role should look like, WorkforceGPT gives an authorized AI agent access to a workforce intelligence engine designed specifically to define work. It establishes not only which skills matter for a role, but the level of capability required—creating a consistent foundation for assessing readiness, identifying gaps, developing employees and planning future talent needs.

For HR leaders, that creates a faster path to building and maintaining the role and skills architecture needed for talent management. For line managers, it reduces the work required to define roles, identify required capabilities and review what employees need to learn or demonstrate to become ready for future opportunities.

AI is making it dramatically easier to create content, but workforce decisions require more than content. They require trusted data about the work itself,” said Linda Ginac, CEO of TalentGuard. HR and business leaders need to know what capabilities a role requires, what good looks like at different proficiency levels and how that information connects to development, mobility and succession. By bringing WorkforceGPT into the AI agents people are already using, we can make that intelligence available at the point of work rather than requiring people to start in another application.”

From Job Description to Governed Role Intelligence

Through the WorkforceGPT connector, an authorized user can currently ask an AI agent to perform two core functions.

• First, WorkforceGPT can analyze an organization’s existing job description and return a score, explain what that score means and identify information that should be strengthened in the source document. The assessment measures how much of a structured role profile can be supported by the information contained in the job description rather than relying on AI to fill critical gaps.
• Second, WorkforceGPT can build a structured role profile from a job title and organization name. The resulting profile can include a role description, responsibilities, required skills, proficiency expectations and learning resources. Organizations can currently select learning resources from LinkedIn Learning or Skillsoft.

The distinction between identifying a skill and defining its required level is critical. Knowing that a role requires a skill does not tell an organization how capable someone needs to be to perform that role successfully. By establishing target proficiency expectations, WorkforceGPT creates data that can be used to assess employee readiness, identify capability gaps, guide development and compare talent consistently across roles.

WorkforceGPT grounds skills using labor-market and organizational data, including information from the O*NET database. When appropriate occupational data is unavailable, the system can use the organization’s own job information as the grounding source. TalentGuard’s workforce-specific models then generate and structure the additional role information around that foundation. This approach is designed to reduce one of the most significant risks associated with using general-purpose generative AI for talent management: creating plausible-sounding workforce data that has not been grounded in an organization’s actual work or an established labor-market source.

Building the Data Layer Talent Systems Depend On

Every major talent process relies on a common chain of workforce intelligence:

Role → Responsibilities → Skills → Proficiency Definition → Target Level → Employee Capability → Gap → Development → Readiness

Role and skills data sits beneath many of the most important processes in talent management, including career mobility, employee development, succession planning, learning, talent assessment and workforce planning. Yet many organizations still have incomplete job descriptions, inconsistent skill definitions and outdated role information distributed across HR systems, spreadsheets and documents.

That underlying structure supports career mobility, employee development, succession planning, learning, talent assessment and workforce planning.

Yet many organizations still have incomplete job descriptions, inconsistent skill definitions, no common proficiency framework, unclear target expectations, and outdated role information distributed across HR systems, spreadsheets and documents.

“Talent systems are only as useful as the workforce data underneath them,” said Frank Ginac, Chief AI Officer and Chief Technology Officer at TalentGuard. “A skills list alone is not enough. Organizations need to know which capabilities matter, how proficiency is defined, and what level each role requires. WorkforceGPT creates that foundation in a consistent, structured way using labor-market intelligence and the organization’s own role data. MCP now allows organizations to make that intelligence available directly to the AI agents their teams are beginning to use every day.”

Because MCP is an open protocol, WorkforceGPT is not limited to a single AI platform. Organizations can connect MCP-compatible applications and agents to the same WorkforceGPT service, creating a consistent workforce intelligence layer that can support multiple AI-enabled workflows.

Access is controlled at the WorkforceGPT account level. An authorized user approves the connection through the browser, and subsequent requests operate within the permissions and usage allowance of that account. The role profiles and job-description assessments generated through the service describe organizational roles and work requirements rather than individual employee records.

Why It Matters Now

Generative AI has made it easy to create job descriptions and lists of skills. But enterprises need more than generated content to make workforce decisions. They need a consistent definition of each role: what the person is responsible for, which skills the role requires, what proficiency looks like, and what level of proficiency is expected.

That structured workforce data becomes the foundation for decisions made by both HR and line managers. It allows organizations to assess whether employees are ready for their current or future roles, identify capability gaps, target development, find internal talent, build succession pipelines and understand workforce readiness. An AI agent may be able to draft a job description, recommend training or discuss career opportunities, but those outputs become significantly more useful when the agent can reference a governed definition of the role, its required skills and the proficiency expected for each capability.

By making WorkforceGPT available through MCP, TalentGuard allows AI agents to access governed workforce intelligence directly instead of attempting to infer or recreate it independently. Organizations can use the same structured role data to support TalentGuard’s talent management applications or downstream platforms such as SAP SuccessFactors, Workday, PeopleSoft and other enterprise systems.

The WorkforceGPT MCP service is available at https://workforcegpt.ai/mcp.

About WorkforceGPT

WorkforceGPT is TalentGuard’s proprietary workforce intelligence engine for building and maintaining structured role and skills data. Unlike a general-purpose language model prompted to generate HR content, WorkforceGPT uses a mixture-of-experts architecture composed of workforce-specific models trained and calibrated around labor-market information, role taxonomies, industry competency frameworks and organizational skill standards.

WorkforceGPT can generate and govern job descriptions, responsibilities, skills, proficiency frameworks, target proficiency expectations and learning alignment—creating the structured role architecture organizations need to evaluate capability and readiness consistently. Outputs are designed to support governance, versioning and subject-matter-expert review before being used in talent management processes. TalentGuard uses WorkforceGPT as the workforce intelligence foundation for its own talent management platform, and organizations can also use the resulting role and skills data with other enterprise HR systems.

About TalentGuard

TalentGuard is a workforce intelligence company that helps organizations understand the work they need, the capabilities their people have and the gaps they need to close. Its platform connects role architecture, skills intelligence, talent assessment, development, career mobility and succession planning so HR and business leaders can make workforce decisions using consistent, governed data.

TalentGuard is headquartered in Austin, Texas.

Learn more at www.talentguard.com.

Claude is a trademark of Anthropic, PBC. O*NET® is a trademark of the U.S. Department of Labor, Employment and Training Administration. All other trademarks are the property of their respective owners.

Media Contact

Leo Murphy
Marketing
info@talentguard.com