Skip to main content

AI-Assisted Engineering

The Spaceflight Dynamics Framework (SDF) is developed using a modern AI-assisted engineering workflow that combines classical software engineering, aerospace simulation development, and large-language-model-supported collaboration.

The use of AI within the project is not intended to replace engineering decisions, architectural ownership, or technical understanding. Instead, AI is used as an engineering acceleration and structuring toolthat supports iteration speed, documentation quality, architecture exploration, brainstorming, and workflow efficiency.

The project itself — including the simulation backend, architecture decisions, subsystem design, propulsion modeling, frontend implementation, guidance logic, telemetry concepts, and overall technical direction — has primarily been developed independently. The project only recently received its first external contributor.

AI support is therefore integrated as part of a pragmatic engineering workflow: repetitive work can be accelerated, documentation quality can be improved, architectural ideas can be explored faster, and implementation concepts can be discussed interactively while engineering ownership and validation remain human-driven.

Why AI-Assisted Engineering?

Modern engineering workflows are evolving rapidly. Large language models and AI-supported tooling are increasingly becoming part of software development, systems engineering, documentation workflows, and technical communication.

Within SDF, AI is treated as a productivity and engineering support tool rather than an autonomous developer. The goal is not to automate engineering judgment, but to improve iteration speed, maintain architectural consistency, reduce repetitive workload, and accelerate exploration of technical ideas.

This is especially valuable in a research-oriented project environment where architecture discussions, subsystem decomposition, documentation, and future design exploration consume significant development time in addition to actual implementation work.

Current Areas of AI Support

AI support is currently used in several non-critical but highly valuable engineering workflows throughout the project:

  • Architecture brainstorming and subsystem decomposition
  • Frontend structure and UI workflow discussions
  • Documentation drafting and refinement
  • Doxygen documentation support
  • Diagram structure and visualization ideas
  • Release communication and project presentation
  • Issue refinement and milestone structuring
  • Naming discussions and terminology consistency
  • Open-source onboarding concepts
  • Website content and engineering communication
  • Refactoring planning and workflow analysis
  • Research-oriented brainstorming and future direction exploration

Human Engineering Responsibility

AI-generated suggestions are treated as engineering support material and are reviewed before integration into the project.

Architectural decisions, simulation behavior, propulsion models, mathematical formulations, subsystem interactions, validation logic, and implementation choices remain under direct human control.

This is especially important in a technically-oriented simulation framework where correctness, maintainability, traceability, and subsystem consistency are critical.

Examples of AI-Assisted Workflow

Typical workflows within the project often combine human engineering direction with AI-assisted iteration support:

  • Initial engineering idea or architectural problem definition
  • Discussion of subsystem boundaries and responsibilities
  • Exploration of alternative implementation structures
  • Refinement of interfaces, DTOs, or dataflow concepts
  • Generation of supporting documentation and diagrams
  • Final engineering review and manual integration into the codebase

This workflow allows repetitive engineering overhead to be reduced while preserving technical ownership and implementation responsibility.

AI-Generated Assets

Some visual assets used throughout the project — including concept art, presentation imagery, and project-related visual material — are generated using AI-assisted image generation workflows.

Examples include:

  • Website hero images
  • Presentation visuals
  • Recruiting graphics
  • Logo brainstorming and design exploration
  • Concept visualization for communication purposes

AI-generated visual assets are primarily used to support communication, presentation, and project identity rather than technical validation.

Engineering Philosophy

The integration of AI into SDF reflects the belief that future engineering workflows will increasingly combine human expertise with AI-assisted tooling.

Rather than replacing engineering thinking, these tools can improve accessibility, accelerate iteration, reduce repetitive workload, strengthen documentation quality, and support collaborative exploration of complex systems.

The long-term goal is therefore not only to build a spacecraft dynamics framework, but also to explore how modern engineering workflows can evolve in an open, transparent, and technically responsible way.