Dylan J Carty

Building software. Exploring ideas.

I'm a software engineer working on backend systems and applied AI. I also build games and independent software. My interests range from radio and drawing to worldbuilding, philosophy, and practical life beyond the screen.

System field

Systems that have to decide, not only describe.

BuildEngineering and projectsThe systems, games, and tools I spend my time building.ThinkWriting and ideasIdeas and observations from the things I build, read, and learn.ExploreBeyond the codeRadio, drawing, music, land, and games. There is plenty to learn away from a screen.

Engineering

All engineering

How I approach backend systems, applied AI, and the problems that come with making them reliable.

  1. EngineeringAI application architectureBuilding applications around AI models: context, permissions, state, and recovery.
  2. EngineeringAgents and orchestrationCoordinating model calls, tools, and the steps between them.
  3. EngineeringDocuments, extraction, and driftTurning varied documents into structured, usable information.
  4. EngineeringEvaluation and quality controlChecking model behavior before a change reaches a workflow.

Projects

All projects

Project

Enterprise Document Extraction Service

From identifying the need to delivering a shared document extraction service.

A shared document extraction service I conceived, designed, and built independently at USLBM.

Open the project

Conceptual overview
DocumentsExtractionValidationShared serviceVisibility

The same business purpose can arrive in different layouts, terms, and structures. Some follow a template. Others need interpretation.

Structured information, shared by many applications instead of rebuilt inside each one.

A flexible reading still has to be accurate and consistent enough for another system to use.

Different consumers have different requirements. The service has to absorb that without becoming a pile of exceptions.

Predictable behavior, clear interfaces, and a way to see what happened when a result fails.

Project

Enterprise AI Trajectory Service

Identifying the need for AI execution visibility and building the shared service to address it.

A centralized AI trajectory service I conceived, designed, and built independently at USLBM.

Open the project

Conceptual overview
ExecutionRecordCorrelationInvestigationAccount

Decisions, model interactions, tool calls, and intermediate steps before a result.

A consistent account of that activity, so each application does not have to invent its own.

Records structured and related so they can be compared across a workflow.

When a request fails, the path to that point and where the behavior left expectations.

A basis for evaluation, oversight, and governance, beyond a note that something failed.

Project

Procure-to-Pay Automation

Owning backend technical decisions and shaping the AI and agentic approach to purchasing automation.

Backend technical ownership and direction of AI and agentic approaches for procure-to-pay automation at USLBM.

Open the project

Conceptual overview
DocumentsMatchingValidationHuman reviewVisibility

Invoices, purchase orders, and receiving records. They do not arrive in one consistent shape.

Comparing those records. Incomplete or conflicting data is the ordinary case, not the exception.

A result has to be checked before it is treated as reliable.

Some cases need a person. The system should not guess past its uncertainty.

Enough of a record to see what happened when something goes wrong.

Project

Canonvale

Roleplaying where the world, its characters, and your choices continue to matter.

An independent AI-powered roleplaying project focused on a world worth returning to.

Open the project

Conceptual overview
ExploreConnectChooseReturn

The aim is a world the player wants to spend time in.

Characters and relationships give the experience personal meaning.

Player choices should feel meaningful within the setting.

The goal is an experience worth continuing across sessions.

Project

AI-Assisted Game Development Toolchain

From a terrain specification to a checked landscape build.

Tools for creating measured terrain in Cursor and checking Gaea exports for Unreal Engine.

Open the project

Conceptual overview
RequestTerrain specGaeaValidationUnrealNot built yet

I describe the landscape in Cursor. That conversation is not the build.

A measured description of the landscape to be created.

Build the landscape and keep the result connected to the reviewed terrain.

Check that the exported assets are consistent before continuing.

The landscape export is prepared for use in Unreal Engine.

Broader asset and scene workflows remain future work.

Project

Ludex

Diagnostics for systems whose failures are easier to notice than to explain.

A telemetry and observability project for making complex system behavior understandable.

Open the project

Conceptual overview
IngestionSchemaHealthDead lettersDiagnosis

How telemetry enters the record, and what is lost before it arrives.

Validation and cleanup, so the shape of an event does not drift until it cannot be read.

Whether the signals are arriving, complete, and still trustworthy.

Messages that were not processed, kept as evidence rather than discarded as noise.

A path from a failed signal to an explanation of what the system did.

Project

Reverse Engineering Workbench

A place to watch a single-player program, keep the evidence, and separate a guess from an observation.

A local workbench for studying how a single-player program behaves: memory changes, instructions, and the evidence behind a hypothesis.

Open the project

Conceptual overview
ObserveEvidenceInspectRelateHypothesis

Watch a running single-player process and record what changed. This is the start of a question, not an answer.

Keep observations tied to the session that produced them.

Decode a short window of x86-64 with Capstone. A successful decode is not proof the instruction ran.

Review relationships in collected evidence as questions for further investigation.

Write down what I think a value means, and what would contradict it. There is no verified status.

Project

Galleries

A gallery that learns what you choose, then answers with a judgement.

A short psychological game on Steam. The art you choose says something about who you are.

Open the project

Conceptual overview
RoomsChoicesPatternJudgement

Curated rooms of art. There is no combat and no grind.

What you admire, and the questions that steer how a choice is read.

The gallery pays attention where your preferences contradict one another.

An ending shaped by the decisions you made, not by whether they were the right ones.

Research

All research

Independent research and thought, shared alongside my technical and creative work.

Consciousness Beyond the Interface: A Comparative Framework for Simulation and Theistic Creation

Independent working paper · Not peer reviewed

Beyond the code

All explorations

Away from software, I spend time learning about radio, drawing, music, and caring for land. I also enjoy games, strategy, and building fictional worlds.

Knowledge map

Follow the connections between my projects and interests.

Topic

Agents

Coordinating tool calls, handoffs, and stopping rules.

Open

Topic

Memory

What a system or character remembers over time.

Open

Topic

World state

Keeping a simulated world's history and current state consistent.

Open

Topic

Worldbuilding

Creating places, histories, and characters that fit together.

Open

Topic

Telemetry

Collecting useful signals about a running system.

Open

Topic

Cybersecurity

Studying program behavior through reverse engineering.

Open

Topic

Signals

How signals are produced, transmitted, and received.

Open

Topic

Radio

Learning about antennas, propagation, and radio equipment.

Open

Topic

Arguments for God

Classical arguments about God's existence.

Open

Project

Enterprise Document Extraction Service

From identifying the need to delivering a shared document extraction service.

Open

Project

Enterprise AI Trajectory Service

Identifying the need for AI execution visibility and building the shared service to address it.

Open

Project

Procure-to-Pay Automation

Owning backend technical decisions and shaping the AI and agentic approach to purchasing automation.

Open

Project

Canonvale

Roleplaying where the world, its characters, and your choices continue to matter.

Open

Project

AI-Assisted Game Development Toolchain

From a terrain specification to a checked landscape build.

Open

Project

Ludex

Diagnostics for systems whose failures are easier to notice than to explain.

Open

Project

Reverse Engineering Workbench

A place to watch a single-player program, keep the evidence, and separate a guess from an observation.

Open

Project

Galleries

A gallery that learns what you choose, then answers with a judgement.

Open

Research

Consciousness Beyond the Interface: A Comparative Framework for Simulation and Theistic Creation

An independent working paper exploring how an already-conscious participant might experience a simulated world, and how that idea relates to naturalistic and Christian accounts of reality. Not peer reviewed.

Open

I'm still working on my first essays and notes for the site. In the meantime, you can explore the engineering and research pages, or find a project in the archive.

Contact