Florida, USA · Remote

Ben McNulty

AI-Enhanced Senior Software Engineer

AI developer tooling, Test architecture, Reliable LLM features

I build software across backend, frontend and testing, with a growing focus on how people and AI agents work together. I’m interested in new interfaces that make that collaboration useful and controllable, with the context, clear expectations and verification needed to get reliable work done.

Looking for Agent and developer tooling, test and evaluation infrastructure, applied AI engineering, or senior full-stack work on AI-native teams. Open to conversations

Selected proof Follow the evidence.

Three featured examples with the problem, my part and the key decision, then more write-ups on BenLive, my personal site. Each is labeled as current-role work, a personal project or first-person writing.

Orgos: an agent-first organizational OS

A personal agent-first OS I’m building: agent identities, memory, files and flow sequencing live on disk as readable JSON and Markdown, with inference dispatched through an observable queue.

Personal project · AI workflow + Context & team rules + Full-stack delivery

The whole delivery surface, directed and owned

I designed the serverless backend, accessible vanilla-JS frontend, cross-browser tests, media pipeline and gated deploy, and I review and maintain them; AI coding assistants carried out the plans I approved.

Personal project · Full-stack delivery + Test architecture + Interface & spatial

More existing work: Featured projects WebXR version: the Immersive Experience Context-first case study (opens in a new tab) AI Lab apps (opens in a new tab) WebXR gallery rebuild (opens in a new tab) Development portfolio (opens in a new tab) Local Crew code (opens in a new tab) Promptpad code (opens in a new tab)

Seen enough to talk?Read the résuméEmail Ben

Role fit Read the record your way.

Choose the perspective closest to your role, and the career record below highlights the parts it draws on.

Link to this perspective

Career record Roles, in order.

Personal AI projects are covered in the proof and capabilities sections.

  1. QA Automation Engineer III

    March 2022–present
    • AI-assisted development-tooling point person for an eight-person automated regression testing team: set up Kiro, the team’s current AI tool, and own its supporting tooling, as before for Amazon Q Developer, whose version-controlled Rules, Profiles and Prompts I authored.
    • Architected the C# migration of a legacy VB.NET test suite onto a cross-driver adapter that runs Selenium or Playwright under the same test logic; the port is under way.
    • Built and shipped an internal documentation and onboarding app that consolidates the team’s scattered docs into Markdown, with a web view built from the codebase.
    • Drive weekly regression triage end to end, converting manual test paths into automated tests.
  2. Independent Web Developer · McNulty Web Apps

    June 2018–February 2022 · 2012–2014 (separate period)
    • Carried responsive full-stack client projects from the first conversation through launch and support, translating ambiguous requests into practical frontend, backend and deployment decisions.
  3. Frontend Engineer · Menuat

    February 2016–May 2018
    • Shipped digital menu systems from concept to cloud-hosted production, translating brand requirements into responsive, accessible experiences on low-performance, TV-connected hardware.
    • Covered project management in the interim, owning scoping, delivery and support across the client base until a permanent PM was hired.
  4. Full-Stack Developer · Enix Networks

    September 2012–August 2013
    • PHP page servers, contact forms and data handling for client sites.

The same record as a résumé

SPECTRAL WEAVE
Explore the combinations and their evidence.

Capabilities What I bring to a team.

Seven disciplines, each with practices, tools and evidence you can open.

01 / AI workflow

AI-assisted engineering workflow

I work with agents by giving them relevant skills, context and clear expectations, then checking what they produce. My current personal work spans dots, Claude Duet and Muse; Claude Code and Codex are my primary direct coding interfaces. Earlier projects include Local Crew, a local-model orchestrator.

Tools & methods
Claude Code · Codex · dots · Claude Duet · Muse · Ollama · Kiro · Amazon Q Developer · GitHub Copilot
Practices and team fit for AI workflow
  • Give agents the relevant project context, skills and working agreements
  • Choose the interface and model for the work, with a clear handoff between agents
  • Make requests, constraints and expected results explicit before a run
  • Let agents carry work forward within agreed boundaries
  • Keep changes reviewable and check the result against the request
  • Record what changed, what was verified and what remains open
Useful for teams that
are adopting AI coding assistants and want reviewable diffs, explicit authority and verified handoffs rather than unbounded agent output.

At work I set up Kiro, the QA team’s current AI tool, and own its supporting tooling, as I did for Amazon Q Developer before it; that and the AI-assisted porting in the driver migration are QA-team scope. GitHub Copilot is my personal VS Code experience, going back to its beta. Everything else here is personal practice on my own projects and public site.

02 / Context & team rules

Context engineering and team AI rules

I turn scattered information into context people and agents can use. For an eight-person automated regression testing team, I set up Kiro and own its supporting tooling, as I did for Amazon Q Developer. I codify internal engineering standards and procedures in agent-usable documentation, and built a documentation app that brings team material into Markdown and a web view.

Tools & methods
Amazon Q Developer Rules, Profiles & Prompts · Kiro · CLAUDE.md · AGENTS.md · Claude Code skills · Markdown · llms.txt
Practices and team fit for Context & team rules
  • Rules, Profiles and Prompts reviewed in pull requests like code
  • A regression an assistant introduces becomes a new rule
  • One documentation path for new engineers and new assistant sessions
  • One canonical policy file that each assistant’s instruction file points to
  • Docs change in the same pass as the behavior they describe
  • Agent-facing guides such as llms.txt generated from one manifest
Useful for teams that
keep knowledge in people’s heads or scattered docs, and want new engineers and new assistant sessions to start from the same reviewed context.

The Amazon Q Developer Rules, Profiles and Prompts, the Kiro tooling and the internal documentation app are QA-team work for my current employer. The canonical CLAUDE.md and AGENTS.md pattern, Claude Code skills and the llms.txt manifest come from my personal projects.

03 / Test architecture

Verification and test architecture

I start with a question: how could this passing result be false? At work, I architected a legacy suite’s move to C# on an adapter that runs the same tests through Selenium or Playwright. The port is under way. In my personal AI Lab, I audit test runners so interrupted batches cannot report success, and turn bugs I find into automated checks.

Tools & methods
C# · Playwright · Selenium WebDriver · Cross-driver adapter · Page objects · axe-core · Firebase Emulator
Practices and team fit for Test architecture
  • Test runners audited so a killed batch cannot report green
  • Every hand-found bug becomes an automated check
  • Test logic never knows which browser driver runs underneath it
  • Ported tests keep running on the original driver until a switch is judged safe
  • Page objects expose intent, not locators and waits
  • Weekly regression triage, driven end to end
Useful for teams that
carry a legacy suite, are changing drivers or frameworks, or are letting AI assistants touch code, and need a passing build to mean something.

The adapter migration and regression triage belong to my current QA Automation Engineer III role. Runner audits, cross-browser suites and the bug-to-check rule come from my personal AI Lab.

04 / AI product reliability

Reliable, honest LLM features

I build AI features with clear expectations, visible results and room for the person to direct the work. In my personal AI Lab, chat replies name the model that answered; versioned prompt contracts keep behavior explicit; and an allowlisted model chain with a circuit breaker is designed to return an answer from a smaller model rather than fail.

Tools & methods
OpenRouter · Ollama · Firebase Functions
Practices and team fit for AI product reliability
  • Clear expectations and versioned prompt contracts that make agent behavior reviewable
  • Chat replies labeled with the model that actually answered
  • Allowlisted models, a fallback chain and a per-model circuit breaker
  • System prompts kept server-side behind versioned prompt keys
  • Separate server and client retry policies, each traced to a real failure
  • Interfaces that help people guide the work, inspect results and build trust
Useful for teams that
put language models in front of users, where cost control, honest attribution, privacy boundaries and graceful degradation have to be designed in from the start.

Personal AI Lab work on my own public site.

05 / Full-stack delivery

Full-stack product delivery

I take web products from the first request through deployment and support, in TypeScript, JavaScript, React, Next.js, Node.js, C# and PHP. As an independent developer I carried client projects from the first conversation to support; earlier I built PHP client sites at Enix Networks. My recent personal work includes a serverless AI backend that I designed, built with AI coding assistants and maintain as its only engineer.

Tools & methods
TypeScript · JavaScript · React · Next.js · Node.js · C# · PHP · REST APIs · SQL/NoSQL · Firebase
Practices and team fit for Full-stack delivery
  • Serverless backends on Firebase Functions and Firestore
  • Rate limiting keyed on an HMAC of the visitor’s IP, never the raw address
  • Personal-site deploys gated by model probes and post-deploy smoke checks
  • One shared module where a configuration had been forked
  • Client delivery from first conversation through deployment and support
  • PHP page servers, contact forms and data handling
Useful for teams that
need one engineer to carry a feature across backend, frontend, tests and deploy, and to explain the tradeoffs between those layers.

The Firebase and serverless work is my personal AI Lab. Independent Web Developer, June 2018–February 2022. Full-Stack Developer at Enix Networks, September 2012–August 2013.

06 / Interface & spatial

Interface, motion and spatial UI

I build responsive, accessible interfaces, from advanced CSS and design systems to spatial UI. At Menuat I shipped animated digital menu systems on low-performance, TV-connected hardware. For my own site I directed a Codex-assisted rebuild of a Three.js and WebXR gallery, with hand-tracking grabs, intent-safe teleport and an AR miniature, and kept a route that needs no 3D.

Tools & methods
CSS · Three.js · WebXR · ARIA · Container queries · oklch · cannon-es
Practices and team fit for Interface & spatial
  • Animated digital menu systems designed for constrained, TV-connected hardware
  • Brand requirements translated into responsive on-screen experiences
  • Hand-tracking grabs, intent-safe teleport and a hand-held AR view
  • Design systems built on oklch, clamp() type and container queries
  • Contrast checked in both themes; focus kept keyboard-safe
  • A stable, readable reduced-motion version of every effect
Useful for teams that
build visual or immersive products that must stay readable, accessible and smooth on real devices, not only in a desktop browser.

Frontend Engineer at Menuat, February 2016–May 2018. The WebXR gallery and site visuals are personal, AI-assisted projects that I directed and verified.

07 / Collaboration

Communication and handoffs

I connect the people and disciplines a project needs: users, design, frontend, backend and testing. At Menuat I was the frontend intermediary between users, design and backend. I make expectations clear, write down decisions and leave handoffs someone else can pick up; those habits also shape how I collaborate with agents.

Tools & methods
Decision logs · Handoff notes · Markdown docs · Pull-request summaries
Practices and team fit for Collaboration
  • Every run ends with a handoff: what changed, what was verified, what was not
  • Decision logs record why, so settled questions stay settled
  • Handoffs designed so a qualified stranger could continue safely
  • Briefs that ask for plain, action-first on-screen copy
  • Candid retrospectives, including what did not work
  • Frontend intermediary between users, design and backend at Menuat
Useful for teams that
work remotely and in writing, and need someone who leaves work in a state that other people, or assistants, can pick up.

Frontend Engineer at Menuat, February 2016–May 2018. The rest is practice shown in my own writing and projects.

Where the evidence is Every write-up the chapters cite, and which chapters cite it. Numbers open a chapter; titles open the write-up.

ChaptersAI workflowContext & team rulesTest architectureAI product reliabilityFull-stack deliveryInterface & spatialCollaboration

Where the skills meet The value is in the combinations.

Hiring for one skill rarely fills a role. Each pairing below joins two disciplines in one project or article you can open.

Every pairing at a glance Each mark is one of the pairings below, where two disciplines meet in work you can open; choose one to read it.
DisciplineAI workflowContext & team rulesTest architectureAI product reliabilityFull-stack deliveryInterface & spatial
Context & team rulesContext & team rules with AI workflow: Harnesses judged on context hygiene
Test architectureTest architecture with AI workflow: Assistants work inside the test contractContext & team rules with Test architecture: Rules that require tests
AI product reliabilityAI product reliability with AI workflow: Model choice that plans for failureContext & team rules with AI product reliability: System prompts stay on the serverAI product reliability with Test architecture: User-gated AI that stays testable
Full-stack deliveryFull-stack delivery with AI workflow: Assistants run the loop; I own the outcomeNo pairing hereFull-stack delivery with Test architecture: Deploys gated by probes and smoke checksAI product reliability with Full-stack delivery: Abuse protection that respects privacy
Interface & spatialAI workflow with Interface & spatial: Directing AI design, judged on deviceNo pairing hereInterface & spatial with Test architecture: Automated checks for spatial interactionAI product reliability with Interface & spatial: A user-triggered editor, still under testNo pairing here
CollaborationCollaboration with AI workflow: Handoffs a stranger could continueCollaboration with Context & team rules: Decisions that stay decidedCollaboration with Test architecture: Handoffs that say what was not verifiedNo pairing hereNo pairing hereCollaboration with Interface & spatial: Plain language on screen
  1. Assistants work inside the test contract

    Test architecture with AI workflow

    Alongside the driver migration, I codify the team’s internal engineering standards and procedures in documentation agents can use. The versioned Rules and Profiles make the adapter contract and expected checks explicit; people own the architecture and release decisions.

    Cross-Driver Test Architecture (opens in a new tab)Current role

  2. Harnesses judged on context hygiene

    Context & team rules with AI workflow

    I rate a coding harness first on context hygiene: it has to read the project’s rules file on every session without anyone pasting it in.

    Models and Harnesses (opens in a new tab)First-person writing

  3. Rules that require tests

    Context & team rules with Test architecture

    The QA team’s repository-owned AI rules require every behavior change to arrive with its matching test update, and changes to those rules are reviewed in pull requests.

    Version-Controlled AI Governance for Engineering Teams (opens in a new tab)Current role

  4. User-gated AI that stays testable

    AI product reliability with Test architecture

    Each model call waits for a click, so end-to-end tests can mock the model and assert the control state at every step. Those tests check the controls; the model’s variable answers are a separate question.

    AI Lab Part 3: Problem Solver (opens in a new tab)Personal project

  5. Abuse protection that respects privacy

    AI product reliability with Full-stack delivery

    The public chat’s rate limiter keys on an HMAC of the visitor’s IP under a secret salt, so raw addresses are never stored or logged.

    Production Resilience Patterns for AI-Powered Features (opens in a new tab)Personal project

  6. Model choice that plans for failure

    AI product reliability with AI workflow

    The rule I use to pick models, the cheapest one that clears the bar for the task, with a fallback, reproduced locally before shipping, is the rule the public chat runs on.

    Models and Harnesses (opens in a new tab)First-person writing

  7. A user-triggered editor, still under test

    AI product reliability with Interface & spatial

    Promptpad shipped a user-triggered inference loop, a revision model and a polished editor together, and the interface stayed testable.

    AI Lab Part 2: Promptpad (opens in a new tab)Personal project

  8. Automated checks for spatial interaction

    Interface & spatial with Test architecture

    Automated checks cover the WebXR gallery’s hand gestures, teleporting and AR entry and exit; headset sessions then look for what the tests missed.

    Rebuilding my WebXR portfolio, one headset test at a time (opens in a new tab)Personal project

  9. Directing AI design, judged on device

    AI workflow with Interface & spatial

    For the October polish pass on my site, I directed the work and judged each change on my phone; Claude did the design and engineering.

    Designing past the AI template, prompt by prompt (opens in a new tab)Personal project

  10. Assistants run the loop; I own the outcome

    Full-stack delivery with AI workflow

    Across my AI Lab’s delivery surface, assistants carry context and execute plans I have approved. I decide what to build, set the constraints, review the plan and the diff, and own the outcome.

    Shipping AI Features End to End as a Solo Engineer (opens in a new tab)Personal project

  11. Deploys gated by probes and smoke checks

    Full-stack delivery with Test architecture

    Before each release of my personal site, the deploy path probes every live model with a tiny request; afterward a smoke script checks status codes and headers.

    Shipping AI Features End to End as a Solo Engineer (opens in a new tab)Personal project

  12. System prompts stay on the server

    Context & team rules with AI product reliability

    AI Lab apps send a prompt key, never a prompt, so system prompts are not shipped to the browser and a visitor can choose only from allowed keys. That narrows what a visitor controls; it is not a guarantee against prompt injection.

    Context Engineering: The Skill That Makes AI Assistants Useful (opens in a new tab)First-person writing

  13. Plain language on screen

    Collaboration with Interface & spatial

    In the brief for my site’s launch reel I asked for implementation jargon to be replaced with plain language that tells the viewer what they can do, then reviewed the on-screen copy Claude rewrote.

    Designing past the AI template, prompt by prompt (opens in a new tab)Personal project

  14. Handoffs that say what was not verified

    Collaboration with Test architecture

    A run is not finished until its handoff lists the files changed, what was verified and what was not.

    A CLI Agent Harness Playbook (opens in a new tab)First-person writing

  15. Decisions that stay decided

    Collaboration with Context & team rules

    A decision log records why each choice was made, so the next person or assistant session starts from settled decisions.

    AI Lab Part 5: Iterative Engineering with AI Assistants (opens in a new tab)Personal project

  16. Handoffs a stranger could continue

    Collaboration with AI workflow

    I design each agent run to end in a handoff that a qualified stranger, person or assistant, could pick up safely.

    Meta Programming the Workflow (opens in a new tab)First-person writing

How I work Working principles.

The principles behind the work, each argued in the write-ups linked above.

  1. Ask how a green result could be false

    Why: Ask how a green result could be false

    A runner that treats a killed process as a pass looks green right up until it matters, so every passing result has to be honest about how it could be wrong.

  2. Harness before model

    Why: Harness before model

    I choose the working loop first, judging its context, change control, verification and handoff, and only then debate which model runs inside it.

  3. Context decides the result

    Why: Context decides the result

    Model quality sets a ceiling. The context an assistant starts with decides how close the work gets to it.

  4. Write the team’s AI rules down

    Why: Write the team’s AI rules down

    Every team using assistants already has rules. They belong in a reviewed file, not in each engineer’s habits.

  5. Spend inference only on request

    Why: Spend inference only on request

    My AI Lab apps do not spend a generation the user did not ask for; the person deciding what happens next is the interface, not a limitation on the AI.

  6. Degraded, not down

    Why: Degraded, not down

    A visitor should get an answer from a smaller model before they get an error from a bigger one.

  7. A stale document is a bug

    Why: A stale document is a bug

    Assistants execute against documentation the way they execute against code, so docs change in the same pass as the behavior they describe.

Teams where this combination fits

  • Engineering teams formalizing how they work with AI assistants

    Assistant rules, prompts and review practice versioned in the repository, with harness and model choices made per task. For an eight-person automated regression testing team I am the AI-assisted development-tooling point person and authored its Rules, Profiles and Prompts.

    Context & team rules + AI workflow + Collaboration

  • Product teams shipping LLM features to real users

    Allowlisted models, fallbacks, honest attribution and privacy boundaries have to be designed together with a tested full-stack implementation.

    AI product reliability + Full-stack delivery + Test architecture

  • Test-infrastructure teams modernizing a legacy suite

    Frameworks or drivers are changing under existing coverage, release gates have to hold during the change, and assistants need written rules before they touch tests.

    Test architecture + Context & team rules + AI workflow

  • Product teams that need a senior full-stack engineer

    One engineer carries a feature across backend, frontend, tests and deploy, and can explain the tradeoffs between those layers.

    Full-stack delivery + Interface & spatial + Test architecture

Next conversation Let’s talk about the work.

Looking for agent and developer tooling, test and evaluation infrastructure, applied AI engineering, or senior full-stack work on AI-native teams. Florida, USA · Remote · Open to conversations.

benmcnulty@live.com