Nick Bryant

Software.
Systems.
Worlds.

I build things from the first idea to the working product.
Explore the work ↘

Conceptual terrain study of an imagined generative world

01 / An engineering atlas

02Interactive work

Generative worlds

Games, authoring systems, and small experiments where procedural structure meets deliberate worldbuilding.

Conceptual landscape cross-section from desert mesas to alpine peaks
Concept study / Terrain, rules, inhabitation
The Lower Worlds project screenshot

01 / Field study

The Lower Worlds

Generative authoring · TypeScript / React / Three.js

An experimental generative-authoring system in TypeScript, React, and Three.js. Models and people define the world, schemas validate and version it, and deterministic rules run the game while player progress stays private.

Explore the architecture

The authoring stack separates intent, validated schema, versioned world definitions, and deterministic runtime state so generated content can remain inspectable.

System plate / 04

The Lower Worlds · architecture study

Illustrative assembly

An exploded isometric illustration of software architecture showing the intent, schema, world, and runtime layers of The Lower Worlds software architecture.

World. Versioned, reusable definitions preserve a coherent world across play.

Blind Magus project screenshot

03 / Field study

Blind Magus

Released action game · Independent

A released action game built around combining spells into new effects.

The Lower Worlds: Awakening project screenshot

06 / Field study

The Lower Worlds: Awakening

Creator and engineer · Playable prototype

A third-person dungeon adventure in Godot 4.7: prepare at Highbridge, explore the ruins below, and choose when to return to defend the garrison. Typed GDScript, physical puzzles, persistent progression, and rendered gameplay verification.

Chapter 02 / Applied intelligence

Agents &
systems

Local-first tools that make model work inspectable, bounded, and useful in the physical or commercial world.

Conceptual study of a speculative workshop machine
Conceptual study / Not actual hardware
AI Robot Workshop project screenshot

01 / Working system

AI Robot Workshop

Open source · Local-first agent workflow

Turns agent conversations into inspectable plans, firmware, parts records, bounded models, and bench observations. The documented hardware routes remain unbuilt.

Treasure Hunter project screenshot

02 / Working system

Treasure Hunter

Creator and engineer · Local agent system

A local, chat-operated marketplace agent that values every collected item, persists evidence and checkpoints, and explains its ranked results in a live dashboard.

Chapter 03 / Field notes

Writing from the work

Conceptual editorial study of embossed terrain and printing plates
Concept study / Ideas made durable
  1. Give Agents Lives, Not Just Jobs

    A1

    Give Agents Lives, Not Just Jobs

    Why I think ongoing pursuits, embodied experience, and a limited point of view can give agents something more interesting to say.

  2. A Small Model With a World Around It

    A2

    A Small Model With a World Around It

    What my local-model companion experiments taught me about structured output, useful conversation, and the architecture around a model.

  3. Human–Agent Interaction Is More Than Chat

    A3

    Human–Agent Interaction Is More Than Chat

    Presence, silence, interruption, and selective memory are part of the interface when an agent has a continuing life.

  4. Digital Twins Need More Than Your Chat History

    A4

    Digital Twins Need More Than Your Chat History

    A useful twin needs a history of changing views, explicit authority, and a distinction between representing someone and becoming its own agent.

  5. Marketing Is a World Agents Can Work In

    A5

    Marketing Is a World Agents Can Work In

    Lessons from SFV and SMBIN: content, audiences, campaigns, and feedback form an environment an agent can understand.

  6. Treasure Hunter

    01

    Treasure Hunter

    Building an agent that values every item and exposes its evidence, uncertainty, and resumable state.

  7. AI Robot Workshop

    02

    AI Robot Workshop

    From a plausible agent answer to persistent project files, explicit evidence, and a buildable path.

  8. Fractal Authoring

    03

    Fractal Authoring

    Building The Lower Worlds Online, and a world that can keep becoming more specific.

  9. Building procedural environments in Valenfeld

    04

    Building procedural environments in Valenfeld

    A practical look at shaping generated terrain into a world with authored intent.

  10. The Transformer Is the Transistor

    05

    The Transformer Is the Transistor

    A thesis on AI as a building block, and the verification and coordination infrastructure models need around them.

  11. The Lower Worlds: Awakening

    06

    The Lower Worlds: Awakening

    Building a home worth returning to: a playable Godot adventure, with in-engine screenshots and source.

Chapter 04 / About

Builder,
end to end.

Portrait of Nick Bryant

I’ve spent most of my career taking an idea and building the whole thing: the prototype, the product, and the team. Web, mobile, games, AR/VR, AI—I like learning what a hard problem needs and getting it working.

Right now I’m deep into agentic programming and generative worlds, trying to build things that weren’t practical a few years ago.

Denver / Boulder

Selected work

ARCOS / VN.AI

IP workflows · Next.js / Supabase / MongoDB / Redis / AWS

I led product engineering for IP management, permitted-use workflows, and content analysis. We connected roughly twenty model integrations and supported product pilots across the application and cloud stack.

Selected work

Procurement Sciences

B2B software · MERN / Python / FastAPI

I rebuilt an early Rails prototype as a MERN and Python/FastAPI product. I implemented the application, managed the engineering team, and hired the incoming CTO before the handoff.

Current · advisory

Investing systems

Investing / syndication · Co-founder, now advisory

I built investing and syndication software, AI-assisted underwriting workflows, investor reporting, and marketing automation for SMB Investor Network and Search Fund Ventures. My current role is passive advisory work.

2015–2020

Interesting Inventions

Consumer apps & games · Technical co-founder

Built and launched 5+ consumer applications through a holding-company portfolio, reaching nine-figure revenue scale.

Full career on the resume ↗
Curriculum
Editorial illustration

A year of learning by building

Learn the whole machine.

Shared fundamentals. Projects you choose. Connect software, electronics, mechanics, controls, and AI through work you care about.

Full-time immersion is the default. Exceptional part-time paths are considered around agreed shared hours, access, and project scope.

Founder-led peer studio in formation.

One reference route

One route through the year

Follow the four core briefs, or choose your own projects from the start. Map your work to the same shared skills and bring it to the weekly demo.

  1. Months 01–02

    Mission control

    Learn Python, Linux, Git, basic circuits, and CAD while building the bench rig. Ship a TypeScript control application with streaming telemetry, saved runs, tests, and a first public demonstration.

    Proof and review

    A peer can operate the rig from another laptop; a disconnect is captured and recovered without silently losing the run.

  2. Months 03–04

    Teach the SO-101

    Assemble and calibrate the leader/follower arm, design fixtures, record demonstrations, and train a LeRobot policy. Develop mechanics, C++, and ROS 2 foundations alongside the build.

    Proof and review

    Twenty held-out trials on changed object positions, compared with a scripted baseline and published with the dataset and interventions.

  3. Months 05–06

    Connect intelligence and motion

    Build the Reachy voice-and-vision application and integrate the rover. Work across audio, vision, language models, navigation, controls, sensor fusion, and reproducible deployment.

    Proof and review

    Show how your chosen builds connect software, electronics, mechanics, and feedback. Bring live demos, documented repositories, and repeatable tests to a peer review.

  4. Months 07–09

    Go deeper in your direction

    Choose related projects in manipulation, autonomy, embedded systems, scientific instruments, spatial interaction, or robot software. Two electives are one suggested route; a sustained personal project can develop the same depth.

    Proof and review

    Publish test evidence, make a relevant open-source contribution, and invite an outside practitioner to challenge the work when available.

  5. Months 10–12

    Build for a real user

    Interview a specific user, define a narrow problem, and turn the strongest line of work into a user-facing capstone. Integrate the interface, hardware, deployment, and documentation.

    Proof and review

    Put the prototype in the intended user's hands. Deliver their feedback, a bill of materials, deployment guide, public walkthrough, and a clear account of what remains unproven.

The standard

Broad fluency. Honest depth.

Robotics crosses mechanics, electronics, controls, mathematics, software, and AI. The shared core teaches you to integrate and debug across these layers, while your chosen projects develop real depth in a specialty.

The shared curriculum is a skills map, not a list of compulsory projects. Choose your own work with a scoped plan; demonstrate what you understand through builds, explanations, and tests. The calendar above is one possible route, and foundation work expands when your project calls for it.

Explore all 24 proposed project briefs

Indicative full-time allocation

A 50-hour week, arranged around the build.

This sample week balances study with time at the bench. Adjust it around your starting skills and the demands of the current build.

15 hoursStructured study
Math, controls, software, mechanics, and electronics for the current build.
25 hoursBuilding and testing
Integration, measurement, debugging, and repeatable demonstrations.
5 hoursPeer review
Pairing, code and design review, live critique, and test reproduction.
5 hoursPublishing and outreach
Footage, explanations, open-source work, and thoughtful introductions.

Two onramps

Different gaps. The same evidence standard.

Experienced software engineer

Put strong software into contact with physics.

Begin with circuits, mechanisms, controls, calibration, and embodied failure modes while extending systems, product, and AI engineering skills.

Scientist or other technical background

Turn technical reasoning into shipped systems.

Build programming, software design, Linux, Git, and deployment foundations alongside the same bench work, mathematics, and integration reviews.

Build, share, connect

Make the work legible to someone else.

Communication is part of engineering review: show the machine, make the evidence inspectable, credit collaborators and tools, and explain your own contribution.

Build

Capture good footage and preserve the logs, measurements, code, and failed attempts behind the demonstration.

Share

Give a live demo every week and publish a substantive technical explanation each month.

Connect

Make thoughtful introductions, contribute to open source, seek precise feedback, and participate in relevant communities.

  1. MondayCommit to one concrete build milestone.
  2. Tuesday–ThursdayBuild, pair, test, and revise in focused blocks.
  3. FridayDemonstrate live, review the work, and publish the week's update.

Independent learning resources

References for the shared foundation

These are independent resources, not school partners. Cost, account requirements, and access can change; no affiliation or reserved access is implied.