Available, Los Angeles · Remote / Hybrid

Building the operator layer for AI-native integrations.

I bring a decade of enterprise API integration work across Meta, Yahoo, and Criteo: platform launches, partner enablement, and the handoffs that make complex implementations hold. The operator / AI-native work extends that history with specs, approval gates, and human-in-the-loop workflows for systems that need to ship cleanly.

View resume Selected work Email
ai-operator-system
specs/→ scope and acceptance criteria
reviews/→ implementation checks before merge
handoffs/→ what changed, what remains
operators/→ claude-code · codex working notes
> implementation notes stay with the repo
> human review stays in the launch path
01
$10M+ revenue impact
Across Fortune 100 integrations at Meta, Yahoo, and Criteo.
02
10 years of enterprise SE
Pre-sales, discovery, deployment, and partner enablement.
03
30–45% faster time-to-value
On platform rollouts through repeatable integration playbooks.
Prior platforms
Meta Yahoo Criteo
01Selected work

Projects shaped by implementation discipline.

Operator-layer systems for AI, production-shaped agents, and cross-chain settlement. Every project owned end-to-end, scope, build, review, handoff.
Active Featured Mar 2025, present

AI Operator System

Keeps multiple AI coding agents coordinated on the same repo without losing context, and without shipping code that hasn't cleared a spec and review gate.

Shared file system where specs, review gates, and handoff state live as structured, version-controlled artifacts. Claude Code and Codex coordinate through the same rules; humans sign off at the gates that matter. The operator-layer pattern that makes AI-assisted development actually shippable in a real codebase.

Spec-before-build Human approval gates Claude Code Codex
Author & operator GitHub
02 Shipped

Source

Local-first raw transcript capture

A local macOS app that captures mic, system audio, or both at once, and transcribes the audio on-device with faster-whisper. Existing meeting tools optimize for summaries. I wanted the raw transcript source file, saved locally as Markdown with YAML frontmatter and per-source WAV sidecars, so I can hand it into whatever tool I reach for next.

Python faster-whisper Local-first
How to install (Apple Silicon)
Paste this into Terminal. It downloads the latest release, unpacks Source.app into /Applications, clears the macOS quarantine flag, and launches it. 
curl -L https://github.com/GChaucer/source-transcriber/releases/latest/download/Source.zip -o /tmp/Source.zip && \
	unzip -o /tmp/Source.zip -d /Applications && \
	xattr -dr com.apple.quarantine /Applications/Source.app && \
	open /Applications/Source.app
Apple Silicon only (M1 or newer). Grant microphone access on first launch. First transcription downloads the Whisper model (~150 MB). For system audio capture, install BlackHole separately.
Download GitHub
03 Live demo ↗

Support Triage Starter

Production-shaped agent

Classifies inbound support tickets, asks one clarifying question when needed, and routes cleanly to a human. Returns structured JSON routing decisions, a reference for what a shippable triage agent looks like, including when not to act.

Structured output FastAPI Escalation logic
Reference implementation GitHub
04 Shipped

Opportunity Pipeline

Human-in-the-loop AI

Turns unstructured intake into scored, suppression-filtered, human-approved artifacts. AI worker contracts make a multi-model pipeline inspectable instead of a black box.

Multi-model Human-in-the-loop
Open source GitHub
05 Archived

WaveAIO

On-chain minting & automation platform

Co-founded and led an NFT minting platform end to end. Owned product direction, GTM strategy, contributor coordination, and customer-facing execution from concept through launch.

Co-Founder Ethereum
2021 – 2023 Docs
06 Shipped

Circle CCTP

Cross-chain USDC bridge

Implemented the full burn/mint cycle across Base and Ethereum Sepolia via Circle's Cross-Chain Transfer Protocol. Hands-on work with cryptographic attestation and USDC settlement mechanics.

Circle CCTP ethers.js USDC
Nov – Dec 2025 —
07 Shipped

Uniswap V3

Developer support strategy

Designed a tiered SLA escalation model and phased self-service transition roadmap for the trading API. Covered swap routing, liquidity-pool queries, and multi-channel developer triage.

API strategy Integration playbook
Mar 2025 —
--Writing

Notes on building in practice.

Published April 2026

Building Source, a Local-First Transcriber for Raw Transcript Ownership

I did not build a new transcription model. I built a local-first wrapper around faster-whisper because the existing meeting tools optimize for summaries, and I wanted the raw transcript source file. The writeup covers macOS packaging, mic and system audio capture, model tradeoffs, and what I learned about input quality versus model size.

Read more
02How I work

Four steps, the same loop from discovery to ship.

Most AI integrations don't fail at the model layer. They fail in the space between scope and ship, specs, gates, and handoffs. Ten years of enterprise API work, now applied to agentic systems.

Clients don't pay for APIs. They pay for the outcome the integration makes possible, and for someone who'll see it cleanly through the launch.

Step 01
01

Discover

Map the system, the stakeholders, and the constraints before proposing anything. Most SE failures are scoping failures in disguise.

Step 02
02

Spec

Write down scope, acceptance criteria, and the exceptions worth handling. The integration, not the API, is the product.

Step 03
03

Review

Human approval at the gates that matter. Suppression rules, exception paths, and fallbacks, not just the happy path.

Step 04
04

Ship

Optimize for the handoff as much as the launch. Documentation, ownership boundaries, and repeatable patterns are part of the deliverable.

03Experience

A decade at the enterprise API layer.

Pre-sales solutioning, developer enablement, and integration strategy for Fortune 100 advertisers, the operating environment where AI-native workflows now ship.
Jun 2023, Apr 2025
Remote

Technical Solutions Consultant

Lead technical consultant for enterprise API integrations on Meta's advertising platform. Drove adoption through developer enablement, integration playbooks, and cross-functional product feedback loops across Conversions API, Signals, and Measurement surfaces.

30–45% faster time-to-value
Enterprise rollouts
Playbook author
Discovery → deployment
Nov 2020, Feb 2023
Los Angeles, CA

Solutions Engineering Manager & SE

Led technical strategy, pre-sales solutioning, and developer onboarding for API-powered advertising products supporting global enterprise advertisers. Built and authored the SE playbook across S2S integration strategy.

$10M+ S2S revenue impact
Fortune 100 clients
25–35% faster time-to-launch
SE playbook author
Jan 2019, Nov 2020
New York, NY

Solutions Engineer

Owned technical discovery, pre-sales solution design, and integration strategy across e-commerce partners. Full-stack integration consultant across API and catalog-driven personalization pipelines.

$3M weekly revenue lift
Tier 1–3 client ownership
45% faster implementation
S2S & JS integrations
04Technical surface

Where I'm hands-on.

A working surface, not a list of buzzwords. Depth across the integration layer, with current focus on agentic orchestration and payments / web3 settlement.
01
AI & Orchestration

Claude API, OpenAI, multi-model pipelines, Claude Code, agentic workflow design.

02
Payments & Web3

Circle CCTP, Uniswap V3, Plaid API, ethers.js, Base Network, EVM.

03
Enterprise Ad Tech

Meta CAPI, Yahoo DSP API, Criteo API, a decade of production API integration depth.

04
Languages & Tools

Python, JavaScript, TypeScript, REST, GraphQL, Postman, Git.

05Contact

Let's work together.

Open to Solutions Engineer, Partner Engineer, Solutions Architect, Technical Solutions Consultant, and AI Deployment / Forward Deployed roles. Based in Los Angeles, remote or hybrid. Usually replying within a day.

Email
kevinmhouston1@gmail.com
LinkedIn
linkedin.com/in/kevinmhouston
GitHub
github.com/GChaucer