ModelwareACADEMY

Course · NSSE

Neurosymbolic Systems Engineering

From ontological modeling to AI-assisted engineering, built on open standards with hands-on practice.

Taught byDr. Maged ElaasarFounder, ModelwareSystems Engineering MethodologistView instructor profile
  • Start anytime, no cohort required
  • Course slides and recorded videos
  • 1-hour live office hour every week
  • Hands-on exercises and full project, with feedback
  • 6-month evaluation license of OML Code

WAYS TO TAKE IT

Choose How to Enroll

Payments are processed by Paddle, our merchant of record. Your receipt and invoice come from Paddle, and sales tax is calculated at checkout. Your statutory 14-day refund right ends when the course materials are first shared with you, or 14 days after purchase, whichever comes first.TermsPrivacyRefund policy

Not sure yet? Ask us a question

WHY IT EXISTS

Your engineering knowledge is connected. Is it computable?

Engineering knowledge spans requirements databases, SysML models, spreadsheets, and verification tools. Traceability links connect some of it, but connections alone don't make knowledge computable. Even with MBSE, answering critical questions often requires manual interpretation and analysis.

The challenge isn't a lack of models or connections. It's making engineering knowledge computable enough for automated reasoning, continuous verification, and trustworthy AI-assisted engineering.

Read the case for neurosymbolic systems engineering

WHO IT’S FOR

Engineers ready to make engineering knowledge computable

Designed for systems engineers, SysML and MBSE practitioners, methodology developers, and technical professionals who want to advance their engineering practices. Learn to transform engineering knowledge into semantically rich, computable models, automate reasoning and verification, and integrate generative AI while preserving rigor and traceability.

What you will need
  • Familiarity with an engineering domain you can apply throughout the course.
  • A GitHub account.
  • Willingness to work with VS Code and command-line tools.
No prior OML experience required

No experience with OML, ontologies, or formal reasoning is assumed. The course introduces the foundational concepts and guides you through the tooling and setup in the first module.

WHAT A WEEK LOOKS LIKE

Eight weeks. Eight modules. Real engineering work.

You work at your own pace, on two models at once: the running example, and a system of your own choosing that you build a methodology for as the course goes.

1Study2Apply3Build4Review5Discuss8weeks
  1. 1
    StudyWork through the week's slides and recorded video on your own schedule, shared from Google Drive.
  2. 2
    ApplyAssignments on the running example, a wildfire-response system of systems, where each concept is used on a system you already know.
  3. 3
    BuildApply the same step to a project you choose, developing your own methodology and case study a layer at a time.
  4. 4
    ReviewSubmit both each Sunday and the instructor returns written feedback during the week that follows, with extensions when you need them.
  5. 5
    DiscussA live office hour each week to take up whatever the feedback raised.

Eight consecutive weeks of instruction, then four further months of access. You choose when to start; the eight weeks of assignments, written feedback and office hours run from there. After they finish, the materials and the platform stay open for four more months so you can keep working through your own project.

Delivered directly by Modelware. You will hear from us after you enroll. Slides and videos are shared from a Google Drive, feedback on assignment/project are communicated by email, and your questions are answered on Slack and in live office hours.

COURSE OUTLINE

What You’ll Learn

  1. 1FoundationsFrom Model-Based to Neurosymbolic Systems Engineering

    Explore the evolution from document-centric engineering to MBSE and neurosymbolic systems engineering. Understand how explicit semantics, formal reasoning, and generative AI complement established engineering practices.

    • Understand the principles of ontological modeling and computable engineering knowledge.
    • Distinguish models, metamodels, ontologies, and knowledge graphs.
    • Explore the complementary roles of symbolic reasoning and generative AI.
    • Set up the OML Code development environment and explore the course case study.
  2. 2Representation I: The Basics of OMLMaking Engineering Knowledge Explicit and Machine-Interpretable

    Learn to represent engineering concepts, relationships, and system structures using the Ontological Modeling Language (OML). Develop a formal vocabulary that captures the meaning of engineering information across disciplines and tools.

    • Define concepts, relationships, properties, and constraints in OML.
    • Represent system architectures, requirements, interfaces, and engineering data.
    • Organize models into reusable, modular ontologies.
    • Build and validate an initial domain model using OML Code.
  3. 3Representation II: Reasoning over OMLAutomated Inference and Consistency Checking

    Discover how formal semantics enables computers to interpret engineering models, infer implicit relationships, and detect inconsistencies. Apply automated reasoning to answer questions that traditional model navigation cannot resolve on its own.

    • Understand open-world semantics and the foundations of OWL-based reasoning.
    • Express logical restrictions and engineering rules.
    • Use inference to derive relationships and classify model elements.
    • Detect logical inconsistencies and distinguish them from violations of engineering constraints.
  4. 4Methodology I: Patterns and AuthoringTurning Ontologies into a Repeatable Engineering Practice

    Move beyond individual models to define a systematic modeling methodology. Create reusable patterns and authoring conventions that guide engineers in producing consistent, interoperable engineering knowledge.

    • Design reusable modeling patterns for recurring engineering problems.
    • Define modeling conventions and domain-specific methodology guidance.
    • Structure model libraries for consistency and reuse.
    • Apply the methodology to the course case study and your own engineering domain.
  5. 5Methodology II: Queries, Views, and AnalysesTurning Computable Knowledge into Engineering Answers

    Learn to extract actionable information from connected engineering models. Define queries, generate stakeholder-specific views, and implement analyses that evaluate engineering relationships and constraints.

    • Use SPARQL to query engineering knowledge across connected models.
    • Build reusable queries for traceability, dependencies, and impact analysis.
    • Define views tailored to different stakeholders and engineering concerns.
    • Implement analyses that expose inconsistencies, gaps, and potential engineering risks.
  6. 6Neurosymbolic Loop: AI in the MethodologyCombining Generative AI with Formal Engineering Verification

    Integrate generative AI into the modeling methodology to accelerate engineering work without relying on unverified AI output. Learn how symbolic models and automated checks provide explicit context, constraints, and feedback for AI-assisted engineering.

    • Use AI assistants to generate and refine engineering model content.
    • Ground AI interactions in domain ontologies, patterns, and modeling conventions.
    • Verify AI-generated content using model validation, queries, and reasoning.
    • Apply an iterative generate-check-repair loop to improve model quality and consistency.
  7. 7Engineering Products: Generation and PublicationGenerating Documentation, Reports, and Engineering Artifacts

    Transform integrated engineering knowledge into products that stakeholders can review, exchange, and use. Learn how a single authoritative model source can support multiple engineering deliverables without manually maintaining duplicate information.

    • Generate engineering documentation, reports, and model-derived artifacts.
    • Publish stakeholder-specific views and analytical results.
    • Package engineering knowledge for exchange and downstream consumption.
    • Establish repeatable generation and publication workflows.
  8. 8Models at Scale: Versions, Federation, and CI/CDMaking Neurosymbolic Engineering Sustainable Across Teams

    Scale the methodology from individual models to collaborative, evolving engineering programs. Apply modern software engineering practices to manage changes, integrate independently developed models, and continuously validate engineering knowledge.

    • Manage models using Git-based version control and collaborative workflows.
    • Organize federated engineering knowledge across teams and repositories.
    • Automate validation, reasoning, analysis, and publication using CI/CD pipelines.
    • Establish a repeatable workflow for maintaining trustworthy engineering knowledge as systems evolve.
What you will have built

By the end of the course you will have built two things for a domain of your choice: a neurosymbolic engineering methodology, with its vocabularies, reusable patterns, automated analyses and AI-assisted workflows, and a system model of your own built with that methodology. Both in a version-controlled engineering repository you keep.

WHAT A NEUROSYMBOLIC METHODOLOGY IS MADE OF

The pieces you will build and run

THE NEUROSYMBOLIC LOOP

Generate, check, repair, repeat

A fluent AI assistant and a formal reasoner, each doing what the other cannot, with the methodology between them as the contract.

YouPromptReview1Interpret2Contextualize3Propose4Check5Repair6Explain
  1. 1InterpretAn AI assistant reads prose, documents and intent and identifies key words to ground.
  2. 2ContextualizeThe words are grounded in the model and the methodology, so they are unambiguous.
  3. 3ProposeIt drafts a change in the models and analysis notebooks based on the defined methodology.
  4. 4CheckA reasoner tests consistency, constraints and what follows.
  5. 5RepairThe failures go back as precise instructions the assistant can act on, and it tries again. What it cannot resolve comes to you named, rather than silently.
  6. 6ExplainThe assistant puts the result and the evidence behind it into language you can read, so what you are approving is the reasoning and not just the answer.

Neural: AI assistantSymbolic: model and reasonerYou

THE PLATFORM

See OML Code in Action

Throughout the course, you'll use OML Code to build engineering models, automate reasoning and analysis, and work with generative AI. Watch the demo to see the environment and capabilities you'll be learning to use.

Explore More OML Code Demos

RECOGNITION

Earn Your Certificate of Completion

Receive a Modelware Academy certificate upon successfully completing the course modules and required project deliverables.

The certificate recognizes your demonstrated skills in ontological modeling, automated reasoning, and AI-assisted systems engineering.

Share your achievement on LinkedIn and include it in your professional credentials.

QUESTIONS

Not Sure Yet? Ask Us

Leave your email and a question, or just your email for more about the course. A member of the Modelware team will reply to you directly.

We use your email only to reply to you. Privacy

Advance Your Skills in Neurosymbolic Systems Engineering