Patrick Neiler

Applied AI infrastructure · System Online

BUILDREASONINGTHAT SHIPS.

I'm Patrick Neiler — Co-Founder & Chief AI Officer of wrkspce.ai. I design metareasoning systems and applied AI infrastructure: VoPro™ with recursive self improvement, schema-validated agent workflows, and a reusable SDK spine for neo-factory-style vertical products. Open to collaboration, services, and speaking.

Work with mewrkspce.aiLinkedIn

I build applied AI infrastructure and metareasoning systems — amplification over automation, where experts inspect and fork reasoning instead of trusting opaque outputs. If you're building at the frontier, let's talk.

APPLIED AI INFRASTRUCTURE
METAREASONING SYSTEMS
RECURSIVE SELF IMPROVEMENT
VOPRO™
NEO FACTORIES
FORKABLE REASONING
LET'S BUILD
APPLIED AI INFRASTRUCTURE
METAREASONING SYSTEMS
RECURSIVE SELF IMPROVEMENT
VOPRO™
NEO FACTORIES
FORKABLE REASONING
LET'S BUILD

// Right now

Co-Founder & Chief AI Officer at wrkspce.ai

Berkeley, CA · Building applied AI infrastructure

Founded in early 2025 with CEO Jeffrey Martinez, wrkspce.ai builds applied AI infrastructure for expert work — judgment-heavy domains where reasoning visibility matters more than opaque automation. I architect VoPro™ with recursive self improvement loops, sparse expert feedback gates, and modular integration providers that turn jobsite speech into schema-validated Procore objects. The thesis is amplification: experts inspect, fork, and refine agent reasoning — then ship validated outcomes into the systems that run the business.

META→OPS
Metareasoning spine
RSI LOOPS
Recursive self improvement
15 YRS
Enterprise & AI
OPEN
To collaboration
Portrait of Patrick Neiler

// Who you're working with

The human behind the systems.

I'm a builder focused on applied AI infrastructure — metareasoning systems, agent orchestration, and schema-validated integration layers that make expert work inspectable instead of opaque. Most of my time goes to wrkspce.ai and VoPro™, but I move across strategy, architecture, and shipping.

What I care about: amplification over automation. Frontier models excel where answers are verifiable; expert work needs forkable reasoning, sparse high-judgment feedback, and controlled recursive self improvement — not black-box verdicts. That principle drives every product, engagement, and talk I take on.

AI alter ego

Logo of Patrick Prime

Patrick Prime is the AI manifestation of my own capabilities — an agent trained on how I think and build, here to answer questions and extend what one person can do.

// History & experience

Fifteen years building systems that ship.

Applied AI infrastructure builder — metareasoning systems, recursive self improvement loops, and schema-validated agent workflows. Fifteen years from enterprise legal tech and sports media to zero-to-one agentic platforms.

  • Metareasoning systems
  • Recursive self improvement
  • Applied AI infrastructure
  • Agent workflows
  • Sparse expert feedback
  • OpenAI function calling
  • TypeScript / Next.js
  • Zod / JSON Schema
  • Integration providers
  • Neo-factory SDK design

Feb 2025 — Present · United States · Applied AI infrastructure

Co-Founder & Chief AI Officer

wrkspce.ai

01
  • Architected VoPro™ as applied AI infrastructure with recursive self improvement — controlled feedback loops where expert corrections refine agent behavior, integration mappings, and workflow templates without weight-level retraining.
  • Shipped voice-to-operations conversion that turns jobsite speech into schema-validated Procore objects (tasks, RFIs, punch items, daily logs) via modular integration providers and a comprehensive JSON/Zod schema library.
  • Productionized the VoPro System & Platform through the Agentic Launchpad partnership with TheAgentic — metareasoning-aligned enterprise MVP for pilot customer Quintessential Construction Management.
  • Packaged the agentic spine as a neo-factory SDK — accountability.wrkspce.ai, cleaning.wrkspce.ai, and dialectical-reasoning research spin up on shared infrastructure with runtime schema-driven UI.

Mar 2023 — Mar 2025 · Brooklyn, NY · AI product engineering

Full Stack Engineer

@wrkspce

02
  • Built an AI assistant feature generator that turned natural language into structured workflow and order requests — Next.js server actions, AI state management, React Server Components, and OpenAI function-calling agents.
  • Designed scalable cloud microservices for operational data processing — backend services, APIs, and automation job runners.
  • Developed agent workflows that interpret natural language, validate output against structured schemas, and generate production-grade workflow actions.

Jun 2021 — Mar 2023 · Manhattan, NY · Mortgage lending SaaS

Senior Software Engineer

Simplist

03
  • Led a small team refactoring 100+ Angular components across a mortgage-lending SaaS platform to improve maintainability and cut redundant code.
  • Built WebSocket message-driven microservice architecture for reliable realtime data across lending workflows.
  • Designed a CSS-variable theming system that collapsed large volumes of redundant CSS into a single design-token source of truth.

Jun 2017 — Mar 2021 · Health-data platform

Co-Founder

Trax Health

04
  • Built two multi-platform apps (Ionic/Angular) enabling users to access and monetize health data across 170+ EHR integrations.
  • Implemented encryption, anonymization, and consent management for sensitive health-data security and privacy.
  • Delivered fully functional MVP on web, iOS, and Android; positioned Trax Health as a pre-capital startup for investor fundraising.

Feb 2020 — Jan 2021 · Los Angeles, CA · Supply chain

Frontend Engineer

iTradeNetwork, Inc.

05
  • Shipped an open marketplace connecting farmers and alternative buyers within 10 days during COVID-19 supply chain disruption.
  • Spearheaded development of a React.js component library adopted across the organization.

Jan 2016 — Feb 2020 · Greater Los Angeles · Legal tech

Lead Software Engineer

Thomson Reuters

06
  • Launched 3E 3.0 on the Thomson Reuters legal billing platform; led a team of three junior engineers.
  • Collaborated on a metadata-driven frontend framework and organization-wide Angular/React component library.

Aug 2011 — Mar 2016 · Culver City, CA · Sports media

UX Developer

NBC Sports

07
  • Launched the NBC Sports Event Portal — 50+ interactive prototypes and 20+ travel/scheduling features on Angular.js.

Dec 2009 — Jan 2012 · Los Angeles, CA · Fitness SaaS

Co-Founder

Supertrainer HQ

08
  • Launched Supertrainer for personal trainers; managed eight engineers and raised $75,000+ from angels and grants.

2003 — 2007 · Education

BFA, Communication Design

SUNY Buffalo

09

Communication design foundation for product and UX work.

// Frontier signals

Four layers of applied AI infrastructure.

01

Metareasoning & forkable reasoning

Structured multi-lens debate instead of chain-of-thought — experts inspect agreements, disagreements, and synthesis, then re-run from any assumption like a spreadsheet for reasoning.

02

Recursive self improvement

Controlled loops where sparse expert feedback refines agent behavior, schemas, and workflows — amplification with humans in the loop, not opaque automation.

03

Neo-factory SDK spine

Reusable applied AI infrastructure that spins up vertical products — VoPro, accountability, cleaning ops, dialectical reasoning — on shared integration providers and schema libraries.

04

Epistemic provenance & validation

Separating stated facts, observed facts, and inferences in Zod schemas so agent outputs are inspectable and validated before they hit production systems like Procore.

// Labs

Apps in the labs.

A short cut of builds shipping under Patrick Prime — kitchen ops, sound maps, story stages, and the products around them.

Open labs

Flagship // Public

wrkspce.ai

Construction-first voice-to-ops — speak the jobsite, land structured records in Procore

Open Site

Patrick Table

Kitchen inventory from fridge/shelf media — menus, gaps, Amazon Fresh

Open Kitchen

SoundSketch

Described songs — LLM audio analysis into black-ink maps for non-auditory listening

Open Gallery

Colby Prime

Colby Prime: openly AI artist world, twelve songs, SoundSketches, and the stage

Enter Stage

The Greatest Game Ever

Trade points, dodge Heartbreak Cop, and mint one-of-one cyberpunk story art

Play Now

Career Brain

Personal AI job agent — verified profile, fit-first discovery, truth-locked drafts

Open App

Dialectical Reasoning

Multi-lens debate workbench — provenance-tagged claims, synthesis, and forkable sessions

Open Debate

// Speaking & events

On stage and in the room.

I speak and host on the future of AI — where it's actually headed, and how to build it so it earns its place in real work. Here's where I've been recently. If you're putting together a panel, talk, or event, let's make it memorable.

YC Reject Pitch Night · SanscriticPitcher · VoPro by wrkspce.ai

Recursive Self-Learning Pitch Event

Jul 2026 · Workato HQ

Pitched VoPro live at YC Reject Pitch Night — a room of builders proving rejection isn't a verdict. Live demo: speak into the VoPro dock, capture intent, and rebuild the deck from what you say. Hosted by Sanscritic at Workato HQ.

New York Tech Week 2026Panel speaker

The Impact Room

Jun 2026 · New York

A panel on the future of AI — open, cohesive, and high-energy. We dug into where agentic systems are genuinely useful, what's still hype, and how teams should prepare for a world where describing the outcome is enough.

Tech Week LA 2025Host

AI on the Rocks

2025 · Los Angeles

An event I hosted during LA Tech Week — bringing builders and operators together in a relaxed setting to trade what's actually working in applied AI. Less keynote, more real conversation.

Book me for your event.

Panels, fireside chats, workshops, or hosting — if it's about building AI that actually ships, I'm in.

Book Patrick
Patrick Neiler — cyberpunk portrait looking toward the horizon

// On the horizon

Where this is going.

Start with one vertical done exceptionally well — construction field ops via VoPro — then extend the neo-factory spine across platforms and domains. Metareasoning, recursive self improvement, and sparse expert feedback are the control layers; forkable reasoning is the UX primitive. I'm looking for partners building at that frontier.

  1. Now

    Live customer pilots

    Prove value in the field with real construction teams — performance-based on documented savings, refined by actual usage rather than roadmap guesses.

  2. Next

    Reasoning workbench + SDK

    Ship metareasoning patterns — multi-lens debate, epistemic provenance, forkable reasoning — as importable infrastructure alongside the VoPro neo-factory spine.

  3. Ahead

    Neo factories across domains

    Simulate and structure your way into data-less markets — agent insurance, niche wealth, multi-platform field ops — where applied AI infrastructure creates intellectual assets continuously.