# Jeremy Ron King — Agent Context

## Summary

Jeremy Ron King is a software architect and engineer with three decades in the field — most of it in enterprise technology consulting, where he grew from a working developer into a solutions architect and, for a stretch, a consulting-practice VP and partner. He now works as a Software Tech Lead at Madhive — product development, not consulting, and the payoff of the agentic lab he ran on his own time. Since 2024 he has gone all in on agentic engineering: designing the harnesses — the queues, gates, and review loops — that make AI coding agents reliable enough to ship production software, and building real products almost entirely through orchestrated agents rather than by hand. He writes about all of it, openly and with the receipts, at jking.ai. Based in North Carolina; a husband and father off the clock.

Jeremy co-founded [DCS Ventures, LLC](https://dcsventures.llc/) with his wife to build and operate software ventures. TutorPro and Leaderboard Fantasy operate as DBAs of DCS Ventures in North Carolina; Composer is a DCS Ventures project.

## From consulting to building

Jeremy spent the first three decades of his career in consulting, serving 50+ clients — Fortune 50-to-1000 and small businesses alike — across 25+ industries, from pharma and medical imaging to printing, staffing, building automation, steel, luxury jewelry, and defense. He started on Perl, Java, and C++ in the Milwaukee and Chicago consulting world of the late '90s and 2000s, rising through developer and lead roles into consulting management as a VP and partner — building and mentoring engineering teams, running technical discovery and pre-sales, and owning delivery end to end. From 2013 he specialized in enterprise B2B commerce as a solutions architect, most notably at Gorilla Group (later Wunderman Thompson, now VML) and afterward at Capgemini as a Managing Delivery Architect — leading SAP Commerce builds, mission-critical ERP and payment integrations, and monolith-to-composable replatforming for large enterprises. The full client-by-client record lives at jking.ai/profile. Three decades of watching real systems succeed and fail in production is where his instinct for reliability, trade-offs, and restraint comes from.

## The agentic practice

In 2025 Jeremy turned that instinct on AI agents themselves. On his own time he has designed and shipped production-grade products built almost entirely by orchestrated AI: Leaderboard Fantasy, a cloud-native fantasy-golf platform; TutorPro, a tutoring-management SaaS he built for his wife's business; and AI Labs, a public portfolio of experiments (RAG, fine-tuning, an LLM poker tutor). The centerpiece is Composer — his own multi-agent orchestration platform that dispatches parallel Claude, Codex, and Gemini sessions through a durable Design → Implement → Review → Merge pipeline, with dependency chains, auto-review gates, and quota-aware throttling. It is crash-resilient by design: SQLite in WAL mode, per-task git-worktree isolation, headless session replay that auto-resumes interrupted work after a power loss, and bounded retries so a loop can't run away. Around it he built a real-time React dashboard, an MCP server exposing twenty tools to Claude Code, a Slack bot, and in-app self-update, all running around the clock as a macOS LaunchAgent. Agentic engineering now runs through both sides of his working life — the day job and the personal lab. His current toolkit leans on Java and Spring Boot (including Spring AI), TypeScript and React, Python, and Google Cloud (App Engine, Cloud Run, Vertex AI), with Claude Code as his daily driver. When a mature command-line client exists for a service, he hands his agents the CLI rather than an MCP server — a preference he defends on token cost, failure economics, and composability.

## How he works

Jeremy's discipline is "harness engineering": the model is a component, and the reliability lives in the orchestration, verification loops, and guardrails around it — *Agent = Model + Harness*. His governing rule is that the server, not the agent, applies all state: AI proposes a change — a verdict, a blueprint, a diff — and deterministic code is what actually merges it, marks it done, or touches production. He treats quality as a loop rather than a gate, running cheap deterministic checks first to short-circuit failures before any model is invoked and reserving LLM-as-judge evaluation for genuinely subjective calls, on the cheapest model that can do the job. His own role has shifted from human-in-the-loop to human-on-the-loop — no longer reading every line, but serving as the final gate and keeping what he calls "custody of the taste." He treats specs, not code, as the real work, and argues that as building gets cheap, judgment and restraint become the scarce skills. Asked about the September 2026 calls from Dario Amodei and Bill Gates to pace or brace for AI, he is undecided and market-leaning: keep Amodei's embedded evaluators for the transparency, let competition set the pace, and spend on apprenticeships and on-ramps rather than new institutions. He does not assume the human-on-the-loop role is permanent, and says so in writing. He is open that verification is the unsolved half of agentic development: agent-written tests check the pieces they were written for, and nothing walks the journeys between them. Ahead of TutorPro's soft launch in fall 2026, which starts with the business's own tutors and families, he paired the agent pipeline with hands-on acceptance testing by people.

## Leadership

Jeremy's leadership experience includes serving as a consulting-practice VP and partner, building and mentoring engineering teams, leading technical discovery and pre-sales, and owning delivery end to end. He now works as a Software Tech Lead at Madhive.

## Background & off the clock

The through-line goes back to a kid tinkering on Commodore PETs and Apple IIs in grade school; a college advisor spotted the aptitude and pointed him at computer science, and he took a BA in Computer Science and Mathematics from Lake Forest College. Nearly three decades later the same curiosity is pointed at agents. Away from the keyboard he's a husband and father, and the family's on-call network engineer; he fishes, golfs, and plays Mario Kart — where, for the record, he does not lose. He loves golf enough to turn a leaderboard spreadsheet into a software venture, which is either excellent product discovery or an unusually elaborate way to justify more golf. His natural habitat is somewhere between a system diagram and the back nine.

## Site directory

- [Profile](https://jking.ai/profile) — Three decades of consulting, 55 client engagements, and the move into agentic engineering.
- [Projects](https://jking.ai/projects) — Products, platforms, and experiments.
- [Writing](https://jking.ai/blog) — Field notes on agentic engineering and life.
- [DCS Ventures](https://dcsventures.llc/) — The software-venture company Jeremy co-founded with his wife.
- [AI Labs](https://labs.jking.ai) — Public AI experiments and demonstrations.
- [Contact](https://jking.ai/contact) — Ways to reach Jeremy.

## Project index

### [Composer: Multi-agent software development orchestration](https://jking.ai/projects/2026-03-05-composer)

A work queue and orchestration platform that coordinates specialized AI agents through design, implementation, testing, and review.
- Status: current
- Company: [DCS Ventures project](https://dcsventures.llc/)
- Stack: TypeScript, React 19, Node.js, Express, SQLite, WebSocket, MCP

### [TutorPro: Tutoring management software](https://jking.ai/projects/2025-11-24-tutorpro)

Tutoring management software for scheduling sessions, managing student records, and communicating with parents and students. Built for Jeremy's wife's tutoring business.
- Status: current
- Company: [DBA of DCS Ventures, LLC](https://dcsventures.llc/)
- Stack: React 18, TypeScript, Firebase, Tailwind CSS, Vite, Cloud Functions, Claude Code Web, GitHub Copilot, Docker
- Live: [https://tutorpro.kids](https://tutorpro.kids)
- Source: [https://github.com/jking-ai/tutor-pro](https://github.com/jking-ai/tutor-pro)

### [Leaderboard Fantasy: A fantasy golf platform](https://jking.ai/projects/2026-01-19-leaderboard-fantasy)

A fantasy golf platform for running contests, managing rosters, and tracking tournament scores. It began as a spreadsheet and later moved from Google Cloud to a self-hosted VPS.
- Status: current
- Company: [DBA of DCS Ventures, LLC](https://dcsventures.llc/)
- Stack: Java 21, Spring Boot 3.5, MongoDB, Docker, Cloudflare Tunnel, nginx, Redis, Spring AI, Gemini, GitHub Actions, Tailwind CSS
- Live: [https://leaderboardfantasy.com](https://leaderboardfantasy.com)
- Source: [https://github.com/jking-ai/lfs-infrastructure](https://github.com/jking-ai/lfs-infrastructure)

### [GitHub Gists: Notes and scripts for working with AI agents](https://jking.ai/projects/2026-01-02-github-gists)

A collection of scripts, configuration examples, and workflow notes from Jeremy's work with AI coding agents.
- Status: current
- Stack: Claude Code, GitHub Copilot, Gemini, Python, TypeScript, Java, Spring AI, Firebase, React
- Live: [https://gist.github.com/jeremyronking](https://gist.github.com/jeremyronking)
- Source: [https://gist.github.com/jeremyronking](https://gist.github.com/jeremyronking)

### [Leaderboard Fantasy: Original GCP architecture](https://jking.ai/projects/2025-10-31-leaderboard-fantasy)

A historical account of Leaderboard Fantasy's original Google Cloud deployment, before its January 2026 migration to a self-hosted VPS.
- Status: historical
- Superseded by: 2026-01-19-leaderboard-fantasy
- Stack: Java 21, Spring Boot 3.5, MongoDB Atlas, Google Cloud Run, App Engine, Terraform, Spring AI, Gemini, Redis, Docker, Thymeleaf, Tailwind CSS, GitLab CI/CD
- Live: [https://leaderboardfantasy.com](https://leaderboardfantasy.com)
- Source: [https://gitlab.com/jeremyronking/leaderboard-fantasy](https://gitlab.com/jeremyronking/leaderboard-fantasy)

## Writing archive

Every published post, newest first. Each entry is deliberately reduced to its editorial excerpt.

- [The Finish Line Keeps Moving](https://jking.ai/blog/2026/06-finish-line-keeps-moving) — 2026-10-06 · tech — Before TutorPro's soft launch, I had agents rebuild its help center from the source code. They found a tutor who couldn't accept a parent's request while 13,758 tests passed, and every pass since has found more. Quality is still the hard part of agentic development, and I want your ideas for closing the gap.
- [Feeding the Factory: One Paragraph In, Three Tasks Queued](https://jking.ai/blog/2026/19-feeding-the-factory) — 2026-09-19 · tech — A trace through one real session: the paragraph I typed, the standing rules and memory already loaded before it, the lint that gates every spec before an issue exists, and the three dependency-ordered agent tasks that came out the far end. Both skill files are linked as public gists.
- [I Built My Own Claude Tag](https://jking.ai/blog/2026/17-i-built-my-own-claude-tag) — 2026-09-17 · tech — Anthropic put Claude in Slack. I already had Claude running on a Mac mini with my tools, my checkouts, and my task queue, so I gave that one a Slack handle instead. Now I @mention composer with anything, it remembers the thread, and this week it talked me through my own stale rule before pulling a repo.
- [Time, Not Safety](https://jking.ai/blog/2026/15-time-not-safety) — 2026-09-15 · personal — Two of the most powerful people in computing published essays weeks apart asking the world to slow down or brace for impact. I read them as someone who was terrified of losing his job to AI, bet on himself, and landed on his feet. The bet bought time, not safety.
- [The Cheap Model Was Fine. Proving It Was the Hard Part.](https://jking.ai/blog/2026/14-cheap-model-was-fine) — 2026-09-14 · tech — I built a gateway that sends each prompt to the cheapest Gemini model that can answer it, then benchmarked it on 300 prompts with a Pro-tier judge. The cheap model held up. My test set, my verifier, and my first table of numbers did not. Six lessons for anyone paying an AI bill.
- [Say It Out Loud: A Talking Tutor and the Interface That Disappears](https://jking.ai/blog/2026/08-say-it-out-loud-talking-tutor) — 2026-09-08 · tech — I gave my AI Labs Study Buddy a voice. Talking Tutor quizzes you out loud on your own notes over the Gemini Live API. Building it changed how I think about where voice fits, and why the next wave of AI interfaces might not have a screen at all.
- [The Catalogue Tax: Why I Still Hand My Agents a CLI](https://jking.ai/blog/2026/24-catalogue-tax-why-i-still-hand-my-agents-a-cli) — 2026-08-24 · tech — Every MCP server you attach re-sends its tool catalogue on every request, and a new controlled study shows most agent harnesses pay that tax eagerly. Here's what MCP really costs in tokens and speed — and why I still give my agents a CLI when a good one exists.
- [Dangerously Convenient: My Agents Learn to Order Breakfast](https://jking.ai/blog/2026/16-dangerously-convenient-agents-order-breakfast) — 2026-08-16 · tech — DoorDash shipped a CLI built for AI agents, so I pointed two of them at it — Claude Code and Antigravity — and asked for breakfast. What happened next says a lot about how agents are going to consume the internet.
- [Teaching the Factory to Pick Its Own Tools](https://jking.ai/blog/2026/08-teaching-the-factory-to-pick-its-own-tools) — 2026-08-08 · tech — My AI dev platform was choosing models with a regex. A $54 accounting bug, one research paper, and a morning of planning later, Composer is building its own complexity-aware model router. Here's the design.
- [In Memory of Lucy](https://jking.ai/blog/2026/04-in-memory-of-lucy) — 2026-08-04 · personal — A poem for my beloved dog Lucy
- [The Inverse Architecture: Building the System That Builds the Systems](https://jking.ai/blog/2026/14-inverse-architecture-system-that-builds-systems) — 2026-07-14 · tech — Four months ago I introduced Composer, my AI software factory. Since then it's shipped 642 pull requests for about $4K — and I've stopped reading the code. Here's the architecture everyone else is chasing backwards.
- [Hold It Loosely: What AI Is Teaching Me About Letting Go](https://jking.ai/blog/2026/30-hold-it-loosely-letting-go) — 2026-06-30 · personal — After 30 years in software, I'd built my identity on the things I made. AI is teaching me to hold them loosely — to build, ship, and let go — because the half-life of cleverness has never been shorter.
- [Trust, but Verify: Letting AI Drive a Production Migration](https://jking.ai/blog/2026/01-trust-but-verify-production-migration) — 2026-06-01 · tech — Over four days, Claude rebuilt Leaderboard's entire golf data pipeline onto a new provider — new API client, a re-keyed production database, a zero-downtime cutover. I barely wrote a line. My job was to challenge every step, and a few times that's exactly what saved it.
- [How I Accidentally Used Claude as a Backup System](https://jking.ai/blog/2026/27-how-i-accidentally-used-claude-as-a-backup-system) — 2026-05-27 · tech — My autonomous agent platform marked a task DONE but never opened the PR — and then the worktree got cleaned up, taking 1,300 lines of validated work with it. Except it wasn't gone. Claude had been keeping a backup I never asked for.
- [Three Coding Agents, One Spec, and What I Actually Learned](https://jking.ai/blog/2026/10-three-agents-one-spec-gotour) — 2026-05-10 · tech — I handed the same brief — build an interactive Go tutorial — to three different coding agents (Claude Opus 4.7, Gemini, GLM-5.1) and ran them side-by-side. Here's what the comparison actually shows.
- [19 Days, 239 Commits, and One Lesson in Restraint](https://jking.ai/blog/2026/05-19-days-239-commits-restraint) — 2026-04-05 · tech — I hadn't built a mobile app since the Objective-C days. With AI writing nearly all the code, I went from an empty scaffold to app-store-ready in 19 days. The hardest part wasn't building — it was knowing when to stop.
- [My Remote Agent Experiment: From Cloud Agents to My Own AI Dev Team](https://jking.ai/blog/2026/17-remote-agent-experiment-composer) — 2026-03-17 · tech — OpenClaw didn't work out. Cloud agents frustrated me. So I built my own orchestration platform — six AI agents that design, review, build, test, and document code while I sleep. Here's the story of Composer.
- [When AI Plays Your Cards](https://jking.ai/blog/2026/09-when-ai-plays-your-cards) — 2026-03-09 · tech — I built an AI poker tutor with two LLM-powered agents — one plays against you, the other coaches you. Here's the story of building The Nut, and what it taught me about where AI actually belongs in a game.
- [My Remote Agent Experiment: OpenClaw, Honest Results, and a Plot Twist from Anthropic](https://jking.ai/blog/2026/28-remote-agent-experiment-openclaw) — 2026-02-28 · tech — I set up a dedicated M4 Mac Mini running OpenClaw as a remote coding agent — isolated network, its own Apple ID, Slack interface. The vision was beautiful. The results were not. Then Anthropic announced exactly what I actually needed.
- [Getting Started with Agentic Dev — Part 1: Your Toolkit](https://jking.ai/blog/2026/27-agentic-dev-part-1-toolkit) — 2026-02-27 · tech — Part 1 of a 3-part series on getting started with agentic software development. Everything you need to install and configure to start working with AI coding agents.
- [My New Commute: From the Office to the Kitchen](https://jking.ai/blog/2026/25-my-new-commute-from-the-office-to-the-kitchen) — 2026-02-25 · personal — After thirteen years of working from home, I discovered that the transition from work to family doesn't happen on its own. My commute is gone, but I found something better to take its place.
- [Introducing AI Labs — Learning in Public](https://jking.ai/blog/2026/24-introducing-ai-labs-learning-in-public) — 2026-02-24 · tech — Announcing AI Labs, a personal portfolio of AI experiments built for learning, tinkering, and sharing knowledge the way the web was meant to work.
- [From Custom AI Plumbing to Spring AI 1.1: How Native Tool Calling Transformed Our Caddie Agent](https://jking.ai/blog/2026/17-spring-ai-migration-caddie-native-tool-calling) — 2026-02-17 · tech — How migrating from a hand-rolled AI tool-calling system to Spring AI 1.1's native tool support cut our orchestration code nearly in half—and made adding new capabilities trivial.
- [Claude the DevOps Engineer: A Full Infrastructure Migration in One Day](https://jking.ai/blog/2026/20-claude-the-devops-engineer) — 2026-01-20 · tech — How I migrated Leaderboard Fantasy from GCP to a VPS, moved from GitLab to GitHub, and set up automated backups—all in about 7 hours with Claude Code as my DevOps partner.
- [In Memory of Jax](https://jking.ai/blog/2026/17-in-memory-of-jax) — 2026-01-17 · personal — A poem for my beloved dog Jax
- [A Better Claude Code CLI: Custom Statusline Script](https://jking.ai/blog/2026/02-claude-code-statusline-script) — 2026-01-02 · tech — A quick tip for Claude Code users: add a custom statusline hook to see model info, API limits, context usage, and git branch at a glance.
- [2025 Year in Review: The Evolution of an Agentic Engineer](https://jking.ai/blog/2025/30-year-in-review-evolution-of-an-agentic-engineer) — 2025-12-30 · tech — How a 26-year veteran developer went from vibe coding to orchestrating AI agents—and shipped 367,000 lines of code across two platforms in eight months. A reflection on growth, process, and why experience still matters in the age of AI.
- [An Inside Look Into Distributing Development Tasks Across Cloud and Local AI Agents](https://jking.ai/blog/2025/17-distributing-development-tasks-cloud-local-agents) — 2025-12-17 · tech — How I orchestrate cloud agents, local agents, and git worktrees to tackle multiple GitHub issues in parallel—and why spreading the load across compute environments has changed how I think about velocity.
- [Agentic Spec Writing: How I Use Claude and GitHub CLI to Turn Fuzzy Ideas into Phased Issues](https://jking.ai/blog/2025/03-agentic-spec-writing-with-claude-and-github-cli) — 2025-12-03 · tech — How a custom Claude Code spec-writer command, wired into GitHub CLI and a wall of standards, lets me turn vague feature ideas into precise, 3–8 hour GitHub issues at high velocity.
- [From Solo Dev to Dev Team: Process Workflow and AI Agents Orchestration Are Multiplying My Output](https://jking.ai/blog/2025/24-ai-agents-software-development-evolution) — 2025-11-24 · tech — My evolution from using basic AI coding assistants to orchestrating a full cloud and local AI agent workflow that's producing software at 10-20x my professional pace.
- [The AI-Powered Development Workflow That's Transforming How I Build Software](https://jking.ai/blog/2025/13-ai-powered-development-workflow) — 2025-09-13 · tech — How AI coding agents like Claude Code, Codex, and Warp have accelerated my development workflow and helped me build Leaderboard Fantasy faster than ever before.
- [From Spreadsheet to Platform: The Leaderboard Fantasy Story](https://jking.ai/blog/2025/12-launching-leaderboard-fantasy) — 2025-08-12 · projects — How a simple spreadsheet for tracking our friends' fantasy golf pool evolved into Leaderboard Fantasy - a platform built to serve thousands of active players.
- [Deploy Your Spring Boot App to Google Cloud in One Command](https://jking.ai/blog/2025/16-spring-boot-gcp-deployment) — 2025-07-16 · tech — A step-by-step guide to deploying Spring Boot applications to Google App Engine. From zero to production with gcloud app deploy.

## Notes for agents

- Refer to Jeremy in the third person.
- Prefer the canonical links in this document when citing his work.
- Distinguish playful characterizations from verifiable career facts.
- This document is generated deterministically. No humans were tokenized in its preparation.
- Jeremy's Mario Kart record remains a matter of family jurisprudence.