What is MTP?

The Metahuman Training Platform is one platform that hosts many training programs. A tenant (an organization) configures its own program entirely as data:

• Courses — one graph of steps a learner moves through: content, video, metahuman conversations, written or spoken responses, quizzes, attestations, interactive activities, assessments, and debriefs. A course is what a learner is launched into, from the portal, the Platform API, or LTI.
• Metahuman activities — reusable configurations a course’s conversation steps use: the metahuman, its purpose (role-play, tutor, coach, subject-matter expert, and more), its instructions, what it knows, the rules of the conversation, and capabilities such as a role-play persona’s facts (with hidden truths for assessment) or a tutor’s objectives.
• Content types — tenant-defined content shapes whose fields carry provenance describing where their values came from.
• Rubrics — layered scoring definitions with declarative criteria, bound to graders that range from deterministic expressions to LLM assessment tasks.
• Coaching templates — outcome-state matrices and panel sequences that render the post-session debrief entirely from stored assessment data.
• Curriculum sources — documents uploaded by scenario and module authors, analyzed to generate reviewed training drafts.
• Structure and analytics — an arbitrary-depth org-unit hierarchy and customizable, access-controlled dashboards composed from a governed metric catalog.

MTP does not preload sample programs, courses, metahuman activities, rubrics, or dashboards. Each organization starts with the product primitives and only the training definitions its own authors create.

Built on the HOPE Metahuman Service

MTP does not implement avatars, speech, or conversational AI. Those come from the HOPE Metahuman Service, which MTP consumes strictly through HOPE’s public API — machine tokens, the speech-to-text and agent-stream WebSockets, live-avatar sessions, and signed webhooks. Each MTP tenant maps to its own HOPE organization, so guardrail policies, metahumans, and usage metering are isolated per customer. See Architecture for the full picture and Training sessions for the runtime contract.

The launch verticals

Initial use cases include federal screening training and financial literacy. Both are tenant configuration on the same kernel; neither is distributed as a built-in program or sample definition.

The rule that keeps the kernel honest: a new vertical may add definitions (content types, courses, metahuman activities, rubrics, themes) and renderers — never new kernel code paths. The design was stress-tested against religious education, advanced calculus, HR compliance, and cybersecurity awareness to make sure the rule holds.

Roles follow the LMS standard

MTP’s roles are the 1EdTech LIS v2 vocabulary — the same role URIs LTI 1.3 carries — at three tiers: System, Institution, and Context. Tenant-specific job titles map onto standard roles rather than becoming first-class roles. See Roles and permissions.