KyleSpringfield

Kyle builds data systems and AI tools that make work clearer. In the playground, he experiments with AI-assisted development to broaden his technical knowledge and learn by building.

Proof

Systems built across analytics, data engineering, and AI delivery.

Projects

Flagship systems and applied experiments.

View all
InterCoach interview interface banner preview
Case studyFlagship

intercoach

Real-time AI mock interview app with voice conversations, guided question flow, and instant feedback.

aifullstack
Outcome

Practice with an AI interviewer that adapts to your responses.

Built with
TypeScriptReactViteExpressOllama+3
Sam's Studio platform dashboard banner preview
Case studyFlagship

Full-stack studio management platform with scheduling, bookings, memberships, reporting, and role-based admin/instructor/client workflows.

fullstack
Outcome

Unified scheduling, bookings, and membership workflows in one platform.

Built with
Next.jsSupabaseStripeCapacitor
ecommerce-dbt lineage and model dashboard preview
Case studyFlagship

End-to-end dbt pipeline on DuckDB with tests, docs, and CI.

data
Outcome

End-to-end warehouse modeling with dbt.

Built with
dbtDuckDBSQLCI/CD
Weekform workload intelligence dashboard preview
Case studyFlagship

weekform

Local-first macOS workload intelligence and explainable capacity planning for analysts.

aidatafullstack
Outcome

Groups local foreground-app signals and Outlook calendar events into reviewable work sessions with confidence and evidence.

Built with
TypeScriptReactTauriRustVite+3
xenosync multi-agent orchestration interface preview
Case studyFlagship

xenosync

Multi-agent AI orchestration platform coordinating parallel Claude Code sessions.

aifullstack
Outcome

Coordinates parallel coding sessions across specialized agents.

Built with
TypeScriptNode.jsLLM APIsAutomation
chatdeb analytics chat interface preview
Case studyFlagship

chatdeb

Full-stack chatbot for analyzing business data.

aidatafullstack
Outcome

Conversational layer grounded in business data models.

Built with
FastAPIOpenAILangChainDuckDBdbt+2

Playground

Emberwild: building a survival world for the browser.

Emberwild is an evolving Three.js game where you forage, craft, brave the elements, and build a foothold in the wild. I'm developing its gameplay systems and 3D world with Codex and Claude Code—the latest work-in-progress build is playable below.

Skills

What I ship with in production.

Four connected disciplines, one production-ready delivery practice—from data foundations through deployment.

Capabilities04 production disciplinesMove to reveal

Data Engineering

  • SQL
  • Python
  • dbt
  • ETL/ELT
  • Snowflake
  • AWS
  • Databricks
  • Data modeling
  • Pipeline reliability

Analytics & Measurement

  • Measurement
  • Data Visualization
  • A/B Testing
  • Tableau
  • Streamlit
  • Experiment design

AI Engineering

  • Gen AI
  • AI workflow design

Dev + Delivery

  • Git
  • Bash
  • CI/CD
  • Three.js Game Development
  • Docker
  • Agile
  • Testing
  • Deployment discipline

Now

What I'm exploring right now.

Browse the archive

Current focus

8/9/2026

Weekform at OpenAI Build Week

I'm working on Weekform for OpenAI Build Week, a Codex hackathon focused on turning ambitious ideas into working software.

With Codex as a development partner, I'm building a privacy-minded productivity app that turns local app activity and calendar events into reviewable work sessions, clearer weekly allocation, and capacity insights.

Codex + voice as a project control layer

  • Experimenting with Codex and voice control to coordinate software projects: framing bounded tasks, directing agents, reviewing progress, and keeping related workstreams moving.
  • The practical goal is to spend less time moving context between tools and more time defining the problem, checking the work, and making decisions.

What I’m learning

  • Voice works well for direction and triage; detailed review still benefits from a keyboard and the code in view.
  • Parallel agents help most when ownership is explicit, tasks are narrow, and every result is verified before it is combined.

Contact

Let's talk data platforms, measurement, and AI product acceleration.