Building with Claude since April 2026 · Claude Corps Fellowship

I fell for AI in a chemistry lab. I make systems work smarter.

I'm Vanessa — a PhD chemist who taught myself to build with Claude. I can't look at a process without wondering how to make it more efficient — the ideas start flowing and I have to build them. Apps families use, a free Google Slides add-on anyone can grab (more to come!), tools for industry and research, and an operating system that makes Claude govern, verify and improve itself.

Explore the work → See the system I built

Projects shipped

Live & testable

Automation hooks I built

Operating-system modules

PhD, Green Chemistry · Ogden, Utah · 🇬🇧 🇪🇸 🇫🇷 trilingual+

About me

From the lab bench to shipping software

I spent years as a chemist — a PhD in Green Chemistry, published in mass spectrometry, building machine-learning classification models for cannabis samples long before "AI" was a headline. Some of it was in QC labs under GMP/GLP/FDA rules, where I learnt auditing, traceability and validation fast — the exact discipline my Claude system runs on today. I've also been a teacher and tutor to students all over the world.

Then I started building with AI — and eventually with Claude in particular — and I couldn't stop. With zero formal programming background, I taught myself to scope, ship and improve real products: apps my family actually uses, free tools lots of people can pick up — like a Google Slides add-on I built for my own business — and the system that runs underneath it all, in only a few months, since April 2026.

What I care about is useful, honest work that helps people — which is why most of what I build is free. More than any single field, I'm drawn to making processes better and as efficient as possible. My interests run wide: science, research and industry, education, tools for families, accessibility. Right now, while I homeschool my daughter until she's old enough for public school, learning and family tools are simply where I'm focused — far from the limit of what I want to build.

🎓 Free online teaching 🧑‍🏫 Tools for teachers & homeschoolers 🤝 Exchange teaching ❤️ Charity work 🤍 HG patient peer support 🆓 Free-first software

View LinkedIn ↗

Built with Claude

Things I scoped, shipped & keep improving

Every one of these is a real, working project — most you can open and test right now. My interest runs well beyond teaching, into industry and research too; right now there are more learning tools here simply because that's where my days go, homeschooling my toddler. They're honest first versions: I note what's live and what's next for each, because the work is ongoing.

projects shipped

Portfolio at a glance

14 built with Claude8 earlier, other tools9 live & testablemost of it free

The centerpiece

COS — the Claude Operating System I built

It isn't an app you can open — it's infrastructure. A system of rules, automatic checks and self-audits I engineered so Claude works like a careful, senior teammate: it plans, verifies, logs and improves itself every session — while I stay in the loop, watching, verifying, evaluating, correcting course and making the final call.

🎯

Your request

comes in plain language

✍️

Auto-rewrite

prompt-engineered internally

📚

Playbook loads

right rules, on demand

🔨

Build

with guardrails

🔍

Verify

render + measure, prove it

🔄

Log & retro

never forgets, self-improves

Knowledge modules

Runtime safety hooks

Scheduled automations

Self-audits / month

interactive

Click any step above to see how my system handles it →

Six stages run on every request — from a plain-language ask to a logged, self-improving result.

Self-taught

A system I built — and still supervise

This system is self-taught. I designed and built my Claude operating system independently, drawing on the discipline I developed in regulated QC labs — auditing, traceability and validation — which I consolidated quickly during my short time working there, then refining ideas from the wider community into something more complete. By the time I took Anthropic's AI Fluency and Claude 101 courses, this way of working was already second nature; I passed both 10/10. Their 4D framework didn't teach me these habits — it gave precise names to practices I had already adopted.

Use it→Automate it→Govern it→Auto process-improvement·human input:ReviewFeedbackDecide

🧪 Lab auditing→my system's twice-monthly self-audits

🗂️ Lab traceability→a master index where nothing gets lost

✅ Validation before release→my verify-and-render-before-ship gate

That instinct came from regulated-lab work — picked up fast — and from teaching myself the rest.

⚙️ Automation

Hooks & scheduled audits run themselves — no reminders needed.

🤝 Augmentation

Claude and I build as thinking partners, every session.

🧭 Agency

The COS lets Claude act, verify and self-correct on my behalf.

🧠 Built ADHD-first — which makes it better for everyone

⛔ Perfectionism-loop guard→flags when I'm polishing past the point of real value

📦 Shippability score→tells me the moment a product is good enough to ship

✅ Ship first, refine later→further polish becomes a choice, never a blocker

I designed these guards around how an ADHD brain actually works — but they help anyone: best-quality output, shipped on time, without the hours lost to changes nobody needed.

🎯

Delegation

deciding whether, when & how to engage AI

"Setting goals and deciding whether, when and how to engage with AI." — AI Fluency

On-demand playbook router

The system loads only the rules a task needs, so Claude engages with the right context instead of everything at once.

Mechanism decision guideBEYOND

A rulebook for choosing the right tool for each job — a skill, an agent, a hook or an automation — not just "ask the chatbot".

Cross-tool handoff briefBEYOND

When my free Claude usage ran out, a guardrail let me delegate to a free model (e.g. z.ai) for debugging without it breaking my rules.

Acts autonomouslyBEYOND

It deploys and runs multi-step tasks end-to-end on its own — with a safety guard that forces a private GitHub backup before anything goes live.

Offload to free-running scriptsBEYOND

Whenever possible, work runs as standalone scripts and automations that execute outside the AI's usage — saving cost and stretching every credit further.

✍️

Description

describing goals to get useful behavior

"Effectively describing goals to prompt useful AI behaviors and outputs." — AI Fluency

Auto prompt-engineering hookBEYOND

A dedicated skill turns my everyday, conversational requests into structured, engineered prompts (who / what / context / format) before Claude acts — and when something is vague, it switches to interview mode, asking a couple of clarifying questions first so the brief is right from the start.

Standing rules + power-phrase library

A reusable description system — plain-language conventions, locked decisions — so I never re-explain the same things.

🔍

Discernment

judging whether the output is actually good

"Accurately assessing the usefulness of AI outputs and behaviors." — AI Fluency

Self-preview: render + measureBEYOND

When Claude builds UI, it previews and measures its own work across screen sizes before showing me — so I don't test every little change. Fewer back-and-forths, fewer tokens, better results.

Facts, never assumptionsBEYOND

It double-checks the real sources before speaking — our own files, live documentation for current info, whether a tool/connection is actually available — instead of guessing.

Adversarial critic + a 9-expert boardBEYOND

An internal red-team and multi-perspective panel — each advisor grounded in real methods — review work before it ships.

🛡️

Diligence

taking responsibility for the outcome

"Taking responsibility for what we do with AI and how we do it." — AI Fluency

5 automatic safety hooksBEYOND

Deploy-guard, log-keeper and an auto-retrospective that — at high context — saves my work, then nudges me to free up room. Diligence I can't forget.

A system that improves itselfBEYOND

After each session it scans our conversation for friction and spots new skills, hooks or fixes worth building — then scheduled audits keep everything current, including a weekly agent that revisits every project's saved knowledge and refreshes anything that's gone out of date. Everything is registered, recoverable, and remembered across sessions.

Built-in review mode for human feedbackBEYOND

Every site I build ships with a one-click review mode (this site has it too): I click anywhere to pin a note, then export the whole list for Claude to action — precise human feedback, no guesswork. It's now a standing rule for every website and page my system makes.

Some custom skills I engineered into my system

A few of the reusable skills I built so Claude works the way I need — ordered by how much they shaped this work.

improve-system ★

The self-improvement loop: after each session it scans our work for friction and turns recurring problems into permanent upgrades — the skill that makes the system improve itself.

process-optimization

Reviews the workflow I actually used in a session and finds what to streamline next time — so the way I work keeps getting faster and cleaner, not just the tools.

science-claim-verifier

My scientist's reflex, automated: it checks every health or science claim against peer-reviewed literature before a product ships — and I built it with its own evaluation tests.

ask-the-board

Convenes a panel of advisor personas — each grounded in a real methodology — to pressure-test strategic decisions from several angles before I commit.

Anthropic's courses teach you to use Claude well.
I built an operating system that makes Claude govern, verify and improve itself.

None of it runs unsupervised. I stay in the loop on every build — reviewing the work, correcting it, and stopping to re-steer the direction when needed. The system does the heavy lifting; the judgement stays human.

Where I started

Early projects, other AI tools

Before the system existed, I was already building. These came first — made with other AI tools — and they're exactly why the COS exists now: as I revisit each one, I'm rebuilding it better, the right way.

Honest note: a few of these were debugged with other tools — like z.ai — when my free Claude usage ran out. Building on a budget is part of the story, and stretching free tools is a skill of its own.

Credentials

Certified & always keen to learn

A few of my most recent certifications. During my years in industry at Cytiva and Teva I earned many more — GMP, quality and lab-systems training among them.

🎓

AI Fluency: Framework & Foundations

Anthropic · passed 10/10 ✦

⚡

Claude 101

Anthropic · passed 10/10 ✦

🧪

PhD, Green Chemistry

Loughborough University, UK

🛡️

Safeguarding (Prevent Duty)

UK Government

Let's talk

I'd love to build with the Claude Corps

What pulls me most is purpose. I've chosen most of my roles — including my last, in the QC lab of a medicines manufacturing plant at Teva — because the work reached every patient who needed those drugs to heal or manage their symptoms. That's the thread in everything I build: I want to put my skills to work for the right people, doing the right things — which is why a non-profit or mission-driven team draws me even more than industry. If that resonates, I'd love to talk.

Email me → Connect on LinkedIn ↗