Outcome Based Adaptive Engineering (OBAE)

This document approaches engineering from a parametric modeling underpinning to taking an approach of understanding the end result and incorporating it in the elements of design. We call this Outcome Based Adaptive Engineering (OBAE), and  it combines parametric modeling, generative design, and actionable intelligence. It is a subset of what we call Adaptive Engineering that is the prime basis for Numorpho Cybernetic Systems (NUMO) smart products and services play to enable the proof out of our Mantra M5 (Make+Manage+Move+Market+Maintain) platform for process automation.

We plan to use the Wolfram Language to provide for the engineering design and analysis for the OBAE. It will also provide the basis for an intelligent inference engine for our TAU Codex Transformer that will be trained to automatically design such products in the future using a combination of:

  • themed LLM (Large language model) learning,
  • physics and mathematics
  • multimodal data, and
  • the utilization of images and patterns.

OBAE is based on the construct of Objectives and Key Results (OKR) a goal-setting framework that was popularized by companies like Google and has since been adopted by many organizations, including those in the field of software development. OKRs help teams and individuals define and track their goals and measure their progress towards achieving them. Here’s an overview of OKR and how it enables software development.



Design Innovation is about generating ideas that are desirable, technologically feasible, and financially viable. It is an idea that applies to all fields and people of all backgrounds.

In the endeavor towards Design Innovation, we have to define what we refer to with the term Design with a capital D. Design refers to building human understanding to solve a problem. It is a reference to the relation between things and humans. With this understanding, the outcome of Design varies with the variance in human cultures and lifestyles. In different contexts, design can refer to the hard design practices like product design, engineering design, graphic design, fashion design, and others.


Design Innovation has been growing as its own field for the last half-century. With that came the development of many supporting tools, methodologies, and schools of thought. This growth gave birth to individuals who are more specialized in the processes of Design Innovation.

However, behind all those is the mindset of caring for human needs as much as business ones. Specialized individuals can play a crucial role in facilitating and guiding the process of design innovation within organizations. This is why specialized Design Innovation firms can lead the generating innovations or insights outside the organization.

Many different methods are used to enable Design Innovation. These include Design Thinking, Open Innovation, Innovation Tournaments, Biomimicry, Frame Creation, Design by Decomposition, etc. At NUMO, we will encompass all of the methods to develop a themed curriculum for design innovation that is part of our MANTHAN Innovation Philosophy.




Engineering simulation, which initially emerged in the Aerospace industry, has been the powerhouse for some traditional engineering software providers who have predominantly focused on singular approaches such as Finite Element Analysis (FEA) for structural analysis or Computational Fluid Dynamics (CFD) for fluid flow simulations. In recent times, these providers have expanded their offerings by incorporating multi-physics models and extending their capabilities to domains such as Electronics, Magnetism, Acoustics, and other scientific disciplines.

The advent of GPUs (Graphics Processing Units) has had a significant impact on the landscape of engineering simulation. Previously, software development and its computational aspects heavily relied on writing code and algorithms. However, with the rise of GPUs, hardware has taken center stage in accelerating simulations and computations. This shift has enabled functionalities like ray-tracing and graphics rendering to be available as hardware features, streamlining the simulation process and enhancing visualizations without the need for extensive code development.

This evolution in hardware capabilities has brought about a transformation in engineering simulation, empowering engineers and researchers to leverage more advanced visualization techniques and rendering capabilities. By offloading computationally intensive tasks to specialized hardware, engineers can focus on the actual analysis and interpretation of simulation results, improving overall productivity and efficiency.

The expansion of engineering simulation beyond traditional domains, along with the integration of powerful hardware features, has opened up new possibilities for solving complex engineering problems across various disciplines. This trend highlights the increasing importance of a multidisciplinary and integrated approach in engineering software development, enabling engineers to simulate and analyze the behavior of complex systems more accurately and comprehensively.


Outcome Based Adaptive Engineering (OBAE) is a combination of:

  • Parametric Modeling,
  • Generative Design and
  • Actionable intelligence

utilizing design techniques, simulation and AI/ML to build the next generation of smart and connected products. We plan to use ChatGPT plugged in with the Wolfram Language to enable engineering design, analysis and manufacturing so that the product can be created and understood in unison end to end as it progresses from design to production and beyond.


The Wolfram Language is a highly developed knowledge-based language that unifies a broad range of programming paradigms and uses its unique concept of symbolic programming to add a new level of flexibility to the very concept of programming. It is a symbolic language, deliberately designed with the breadth and unity needed to develop powerful programs quickly.

By integrating high-level forms: Image, GeoPolygon or Molecule – along with advanced superfunctions – such as ImageIdentify or ApplyReaction – Wolfram Language makes it possible to quickly express complex ideas in computational form.

The philosophy of Wolfram Language is to build as much knowledge – about algorithms and the world – into the language as possible. Here are some of its characteristics that we plan to utilize for OBAE:


Key references:

Wolfram Language and Mathematica

The Wolfram Language and Mathematica are closely related, but they have some distinctions:

  1. Definition:
  • The Wolfram Language: It is a general-purpose programming language developed by Wolfram Research. It powers the computational engine behind various Wolfram products, including Mathematica.
  • Mathematica: It is a software application developed by Wolfram Research that provides a comprehensive environment for technical computing. Mathematica includes the Wolfram Language as its programming language.
  1. Scope and Functionality:
  • The Wolfram Language: It is a complete programming language with a wide range of built-in computational and symbolic capabilities. It allows you to perform tasks such as mathematical calculations, data analysis, image processing, machine learning, visualization, and more.
  • Mathematica: It is an interactive technical computing environment that utilizes the Wolfram Language. Mathematica includes the Wolfram Language’s features and extends them with specialized functions and tools for various areas of technical computing, such as mathematics, physics, engineering, finance, and more.
  1. Availability:
  • The Wolfram Language: It is available as a standalone language and can be used in various programming environments and frameworks, both within and outside the Mathematica ecosystem. It is also integrated into other Wolfram products, such as Wolfram|Alpha and the Wolfram Cloud, and more recently as a plug-in into ChatGPT.
  • Mathematica: It is a commercial software application that provides a complete integrated environment for technical computing. Mathematica includes the Wolfram Language and additional specialized functionality. Mathematica licenses are available for purchase from Wolfram Research.
  1. Usage and Context:
  • The Wolfram Language: It is used not only within Mathematica but also as an independent language for computational tasks, algorithm development, prototyping, data analysis, automation, and other purposes. It can be used in command-line environments, notebooks, scripts, or integrated with other programming languages.
  • Mathematica: It is primarily used within the Mathematica environment for technical and scientific computations, symbolic mathematics, data visualization, interactive exploration, and publication-quality document creation.

In summary, the Wolfram Language is the general-purpose programming language developed by Wolfram Research, while Mathematica is a comprehensive technical computing environment that incorporates the Wolfram Language as its programming language. The Wolfram Language can be used independently, while Mathematica provides an integrated environment with additional specialized functionality.


The Wolfram plugin makes ChatGPT smarter by giving it access to powerful computation, accurate math, curated knowledge, real-time data and visualization through Wolfram|Alpha and Wolfram Language.


From their announcement:

“One particularly significant thing here is that ChatGPT isn’t just using us to do a “dead-end” operation like show the content of a webpage. Rather, we’re acting much more like a true “brain implant” for ChatGPT—where it asks us things whenever it needs to, and we give responses that it can weave back into whatever it’s doing. It’s rather impressive to see in action. And—although there’s definitely much more polishing to be done—what’s already there goes a long way towards (among other things) giving ChatGPT the ability to deliver accurate, curated knowledge and data—as well as correct, nontrivial computations.

But there’s more too. We already saw examples where we were able to provide custom-created visualizations to ChatGPT. And with our computation capabilities we’re routinely able to make “truly original” content—computations that have simply never been done before. And there’s something else: while “pure ChatGPT” is restricted to things it “learned during its training”, by calling us it can get up-to-the-moment data.”

Here’s a systematic rundown of how we will utilize ChatGPT, the Wolfram Language, and a scientific/mathematical basis to enable end-to-end engineering design, analysis, and manufacturing for OBAE:

  1. Define the Problem and Objectives: Clearly define the problem statement and the objectives of your engineering project. This could be designing a specific product, optimizing a system, or improving an existing design.
  1. Gather Requirements and Constraints: Identify the requirements and constraints for your project. These can include functional requirements, performance criteria, manufacturing limitations, cost constraints, and any other relevant factors.
  1. Parametric Modeling with ChatGPT: Use ChatGPT to interactively define and modify the parameters of your design. ChatGPT can assist you in generating 3D CAD models based on user inputs, providing design suggestions, and incorporating design changes in real-time.
  1. Generative Design: Employ generative design techniques to automatically explore a wide range of design possibilities. Utilize AI/ML algorithms to optimize the design based on various parameters, such as weight, strength, cost, or other specified objectives.
  1. Simulation and Analysis: Utilize the capabilities of the Wolfram Language to perform simulation and analysis on your design. The Wolfram Language offers powerful numerical and symbolic computation, enabling you to analyze structural integrity, fluid dynamics, thermal properties, and other engineering aspects.
  1. Integration of Design and Manufacturing: Ensure seamless integration between the design and manufacturing stages. The Wolfram Language can help generate toolpaths, optimize manufacturing processes, and provide insights into material selection and fabrication techniques.
  1. Actionable Intelligence and Decision-Making: Leverage the AI/ML capabilities of ChatGPT and the Wolfram Language to provide actionable intelligence. Use historical data, simulations, and real-time analysis to make informed decisions throughout the design, analysis, and manufacturing process.
  1. Iterative Refinement: Engage in an iterative process of design, analysis, and manufacturing refinement based on the insights and feedback obtained. ChatGPT and the Wolfram Language can help facilitate this process by allowing you to iterate and optimize your design quickly.
  1. Validation and Testing: Validate your design through physical testing or virtual prototyping. Utilize simulation tools in the Wolfram Language to validate the design’s performance against the defined requirements and constraints.
  1. Documentation and Collaboration: Document your design process, analysis results, and manufacturing specifications using the capabilities of the Wolfram Language. Collaborate with other team members by sharing code, data, and visualizations to enhance communication and foster teamwork.


By combining the interactive capabilities of ChatGPT, the computational power of the Wolfram Language, and a solid foundation in science and math, we will create a systematic workflow for end-to-end engineering design, analysis, and manufacturing. This approach will enable continuous improvement and optimization throughout the entire product development lifecycle.

This matches with our contention for data engineering wherein it is a combination of training and physmatic (physics + math) based learning and real time analysis that would help prescribe the outcome. Our Mantra M5 Platform would coordinate Make, Manage, Move, Market and Maintain to drive actionable intelligence at every step of the process.

NI+IN UCHIL Founder, CEO & Technical Evangelist


Leave a Reply

%d bloggers like this: