Skip to content
Agentic engineering, done right

Code is now disposable.
Specifications are the product.

I help engineering teams adopt agentic engineering the right way — with the rigor that makes machine-generated code actually safe to ship. The opposite of vibe coding.

Tomas McMonigal · Charlotte, NC + remote

Active Secret ClearanceU.S. Patent Inventor
What I do

Four ways I help engineering teams ship better.

Agentic Engineering Adoption

I coach engineering teams through the shift from writing code to specifying intent. Claude Code & Cursor rollouts, spec-first workflows, and supervisory protocols — so your seniors stop drowning in machine-generated code.

Custom Agent Infrastructure

Athanor-style autonomous pipelines integrated into your dev workflow. Sandboxed Docker, no customer code retention, GitHub-issue-to-PR with triage / developer / reviewer agents and human-in-the-loop checkpoints.

See Athanor →

Specification & Test Rigor

I turn fuzzy PRDs into AI-ready specs: state machines, decision tables, hallucination-proof test suites. The same standards the F-35 BSP team applied to military radios — applied to AI-generated code.

Senior Engineering Work

Hands-on architecture and development. When you need a senior who can ship the thing, not just talk about how to ship it. Backend systems, agent infrastructure, secure networking, full-stack.

Featured work

Athanor — autonomous agent orchestration for GitHub-driven teams

Athanor is a multi-agent orchestration engine I built that autonomously resolves GitHub issues — from triage to pull request — inside isolated Docker sandboxes.

A triage agent analyzes each issue and configures the pipeline. A developer agent owns the full lifecycle inside its sandbox: code changes, git operations, and PR creation. A reviewer agent gates every change before it ships. Humans stay in the loop via dashboard, Telegram, or GitHub comments.

Architecture choices that matter: no customer code retention (every container is destroyed after the job), credential-injection proxies (API keys never enter the sandbox), and dynamic network isolation (agents get internet only when researching). Athanor ships as an on-prem Docker image — I deploy and configure it inside your infrastructure.

LangGraphClaude Agent SDKFastAPIPostgreSQLDocker

Athanor pipeline — issue → triage → developer → reviewer → PR

How I think about this

Typing code is no longer the job.

AI hasn't made engineering easier — it's moved the bottleneck upstream. Code is disposable; specifications are the product. And the supervisor who doesn't understand what the system is doing is the one who crashes the plane.

Specification is the productAgent-sized chunksBlind AI is useless AI
Good fit

Who I work with.

Engineering teams of 5–30 at companies that ship software as a core part of the business.

Teams already using or seriously evaluating Claude Code, Cursor, or similar AI coding tools.

Senior engineers who feel like they're drowning in machine-generated code.

If that sounds like you, we should talk.

About

Hi, I'm Tomas McMonigal.

I started my career on the F-22 and F-35 radio platforms at Collins Aerospace, then shipped embedded firmware for industrial chillers at Carrier, and spent the last few years architecting military VPN infrastructure at SCATR — including the technical implementation behind a U.S. Patent on secure data routing.

The through-line: every system I've shipped has been one where "kind of working" is unacceptable. Military radios. Industrial chillers. Secure VPNs. AI-generated code in production needs the same standard.

Eastwood AI is how I help engineering teams hold that line while moving faster than ever — through coaching, custom agent infrastructure, or hands-on engineering work.

Let's talk.

Free 30-minute intro call. No pitch deck, no sales pressure — we figure out together whether we're a fit.