Paul Martin McNeill / Island of Ireland

Human problems.
Engineered answers.

AI engineering, web development & data analytics.

I connect data, software and AI to build tools for water networks, care, communication and everyday work. Take a look inside.

  • 15+ yearsacross IT, data and engineering
  • MSc Artificial IntelligenceQueen’s University Belfast, due 2027
  • First-Class BSc (Hons)Computer Science, The Open University

Inside the system

From night flows to a weekly plan.

Follow a week of network data from raw flows to where detection crews go next.

Step 1 of 3

Weekly inputs

Night-time flows for more than 1,250 metered areas arrive each week with repair, asset and weather data. The data is noisy, irregular and incomplete, so it is cleaned and checked for anomalies before anything is modelled.

Diagram of the leakage intelligence platform's weekly flow Leakage Intelligence Platform Explore the case study
Interactive architecture walkthroughSelect a stage to inspect it

A few things I’ve built.

Water networks, care systems, communication tools and the data behind them.

Data Analytics

Aurora Domiciliary Care: Power BI Analytics

The problem
Care operations, workforce, finance and compliance need a connected view.
My contribution
Designed a 16-table synthetic dataset, Power Query transformations, DAX measures and six Power BI pages with row-level security.

Early projects, revisited.

Four small apps from 2023. In 2026 I went back, wrote tests, and found bugs in every one. Each case study says what was wrong and how it was fixed.

What I Do

Three disciplines, one practice

AI & Machine Learning

Autonomous agents, RAG pipelines, and tool-calling workflows in production.

  • LangChain
  • GPT/Claude
  • RAG
  • TensorFlow
  • Agents
  • MCP

Web Engineering

TypeScript front-ends, Node APIs, and integrations that hold up under load.

  • React
  • Next.js
  • Node.js
  • TypeScript
  • APIs
  • PWAs

Data Analytics

ETL, modelling, and dashboards leaders actually trust to act on.

  • Power BI
  • Python
  • SQL
  • Pandas
  • ETL
  • Dashboards
AI & Machine Learning

The systems I specialise in

Agents that act, retrieval grounded in real data, predictive models that survive production.

01

Autonomous AI Agents

Plan, call tools, recover from failure — wired into real workflows with guardrails and observability.

  • LangChain
  • OpenAI
  • Claude
  • Tool Use
  • MCP
02

RAG Pipelines & Knowledge Systems

Smart chunking, hybrid search, and grounding so models answer from your data.

  • Vector DBs
  • Embeddings
  • Chunking
  • Semantic Search
03

ML Models & Predictive Analytics

Forecasting, classification, and anomaly detection with proper evaluation pipelines.

  • Scikit-learn
  • TensorFlow
  • XGBoost
  • MLflow
04

Multi-Agent Orchestration

Specialised agents collaborating via function calling, message passing, and structured routing.

  • CrewAI
  • AutoGen
  • Workflows
  • Function Calling
Evidence

Four questions to ask before trusting a model

Each answer below is a measured result from two studies on public data, with the method, the failures and the corrections published beside it.

  • Is the result real?

    0.14 R² from noise

    Choosing a model's inputs before testing it scored 0.14 on shuffled data with nothing to find. That is as high as the real result. Done in the right order, the same recipe scored below zero.

    How it was measured
  • Can anyone act on it?

    75 to 80% false alarms

    Three and seven days ahead, 75 to 80% of the model's high-river warnings were wrong. A band drawn around today's flow, with no model at all, came close: 0.155 against 0.175 on the same score at seven days.

    How it was measured
  • Will it work somewhere new?

    0.850 to 0.752 skill, wet to dry

    A forecasting model trained on wet catchments and tested on dry ones lost about 0.10 of its skill, against 0.03 for a control trained on a random half. A whole region held out of training cost 0.019.

    How it was measured
  • Does the explanation hold?

    0.20 overlap between refits

    Refit the same model on a slightly different sample and its list of the 20 most important inputs changes. On average two refits share about a third of their lists (an overlap score of 0.20). Only two inputs stayed near the top.

    How it was measured
Video

Short explainers of my own work

One to two minutes each, filmed from this site: the Voice app, both studies, the method behind them, and the demos. Every fact in them can be checked on the page each one links to.

  • Voice: an AAC app that explains its predictions

    How a communication app suggests the next word, offline, and says why 1:37

    Transcript

    This is Voice, an AAC app built by Paul McNeill. AAC stands for augmentative and alternative communication: a way to talk for people who cannot rely on speech.

    The user builds a message by tapping words on a board of colour-coded tiles. Every word keeps the same place, in Child and Adult modes alike, so the board can be learned by position instead of searched.

    As the message grows, Voice suggests the next word. Each suggestion says why it was offered, for example a common next word, or a word you often say next.

    The prediction runs entirely on the device, with no network calls. It is a trigram model built from 666 sentences written for Voice, with an optional personal layer and a small ranker on top. Each set of suggestions takes well under a millisecond on a desktop computer.

    Learning is off by default. When it is switched on, Voice learns only from messages that are actually spoken, never from taps that are deleted. Here, after I want Grandma has been spoken three times, Grandma appears as a suggestion, marked as a word you often say next. Everything learned can be seen, and forgotten, one word at a time.

    A caregiver dashboard sits alongside the app. You can try the board, the full app and the dashboard, all with made-up data, on Paul's portfolio at paulmartinmcneill.com.

  • Flood warnings without the weather forecast

    A test across 671 British catchments, and where the skill really comes from 1:52

    Transcript

    Can river floods be forecast without knowing tomorrow's weather? Paul McNeill tested that across 671 British catchments, using CAMELS-GB, a public dataset of daily river flow and weather from 1970 to 2022.

    The task: on any given day, forecast river flow one, three and seven days ahead, using only what is known that day. The models were trained on 1970 to 2004, tuned on 2004 to 2012, and tested on 2012 to 2022.

    Skill is measured with a score where 1 is a perfect forecast and 0 is no better than the long-term average. Most of the skill beyond a day depends on knowing the weather. At seven days, the median score is 0.24 without future weather, and 0.72 when the model is given the weather that actually happened. That second number is an upper bound, not a forecast.

    Forecasting a whole region the model never saw costs little: a median loss of 0.019 at one day. A different climate costs much more. Trained on wet catchments and tested on dry ones, the score falls from 0.85 to 0.75.

    A neural network, an LSTM reading a year of daily data, did no better than gradient boosting. That points to the missing weather forecast as the limit, not the choice of model.

    Warnings are harder still. At seven days, most high-flow warnings are false alarms. The study has not been peer reviewed, and every decision, including the mistakes, is logged in public.

  • Why most cancer drug response stays unexplained

    924 cell lines, one known marker, and a common mistake measured 1:39

    Transcript

    One gene, PTEN, is a known but incomplete guide to how cancer cells respond to drugs that block a protein called AKT. This study asks how much more wider molecular data can explain, using 924 cancer cell lines from the public GDSC screen.

    PTEN alone explains about 5 per cent of the variation in response. Adding cancer type and sequencing centre takes that to 11 per cent. Adding two thousand genes reaches 14 per cent with an elastic net, and 19 per cent with gradient boosting.

    So more than four fifths of the response stays unexplained. And that gap is not mainly measurement noise. A related drug was measured twice: about 80 per cent of its variation repeats, yet the best model for it explains only 18 per cent.

    The study also measures a common mistake. Choosing genes by their link to the response before cross-validating produces a score of 0.14 even on shuffled data, where there is nothing to find. Choosing inside each fold removes the leak.

    The explanations were not stable either. The top twenty genes of refitted models overlap by only 0.2, and no stable subgroups were found beyond tissue of origin.

    Cell lines are a stand-in: nothing here is about patients or treatment. The study has not been peer reviewed. The code, protocol and decision log are public.

  • Six rules for research you can check

    How two reproducible studies were run, and the mistakes they caught 1:32

    Transcript

    Two studies, one set of rules. This is how Paul McNeill runs machine learning research that someone else can check.

    Protocol first: the design is written and dated before any model is fitted, and any later change is a dated amendment.

    Baselines first: every model is compared with the simplest thing that could work, on exactly the same held-out data. The data splits are saved once with a fingerprint, and the code refuses to overwrite them.

    Nothing is learned from held-out data: feature choice, scaling, gap filling and tuning all happen inside the training data. What counts as this did not work is set in advance, and negative results are reported.

    And every decision is logged, including the mistakes. In the river study, the first diagnosis of a weak baseline was wrong; a controlled comparison showed the cause was the target scale. In the drug study, gains were first computed on averaged predictions, which flattered the less stable model. Both were corrected in public.

    Both studies were built making use of AI tools, under research rules Paul set, and each study's log records how. Re-run on a second machine, the main results matched almost exactly; one river experiment is still to be repeated. Neither study has been peer reviewed.

  • A portfolio you can listen to and talk to

    Narration, a voice assistant and a voice picker on paulmartinmcneill.com 1:16

    Transcript

    Paul McNeill's portfolio is built to be heard as well as read. The main pages have a short recorded narration, with the full transcript one tap away.

    The narration uses an AI voice made with ElevenLabs, and every player says so. It is not Paul's voice.

    The site's text assistant can be used by voice too. Press the microphone and speak; the question appears as you talk, and the reply can be read aloud.

    Visitors can choose that voice, the same way they choose the colour and the font. The picker lists the voices on their own device, with a speed control and a preview, and the choice is remembered in their browser.

    On the Lab page there is also a live voice assistant. It answers questions about Paul's work from a fact sheet taken from the site, and says it is not Paul. Nothing from ElevenLabs loads until the visitor presses the button.

    All of it is plain HTML, CSS and JavaScript on a static site. Speech recognition and the voice picker use speech features built into the visitor's browser, and the site still works with no sound at all.

  • Four AI demos in one web page

    A sentiment model, a word predictor, a voice assistant and an agent animation 1:08

    Transcript

    The Lab on Paul McNeill's portfolio holds four working demos. Three of them run entirely on the visitor's device.

    First, a sentiment model. It is a small public example model from TensorFlow.js, trained on movie reviews. Type a sentence and it scores how positive it is, inside the visitor's browser, with nothing they type sent to a server.

    Second, the word board from Voice, Paul's AAC app. It runs the app's real prediction engine, so the suggestions and their reasons match the app.

    Third, a live voice assistant built with ElevenLabs. This is the one demo that uses a server: what the visitor says is sent to ElevenLabs, and the page explains that before anything loads.

    Fourth, an animation of how a research agent works through a task: input, planning, tool use, memory, synthesis and output. It is an illustration of the pattern, not a live agent.

Narrated with an AI voice made with ElevenLabs. It is not Paul’s voice. Captions are part of each video, and every one has a transcript.

Stack

What I'm fluent in

Daily driver

Tools I reach for first.

  • Python
  • TypeScript
  • React
  • Node.js
  • Power BI
  • Pandas
  • Git
  • OpenAI API
  • Claude API
Strong working knowledge

Comfortable shipping in production.

  • TensorFlow
  • Scikit-learn
  • LangChain
  • Next.js
  • PostgreSQL
  • Firebase
  • Docker
  • Azure
  • AWS
  • DAX / Power Query
  • PyTorch
  • Hugging Face
  • MLflow
  • Kubernetes
  • GCP / Vertex AI
  • Jupyter
  • Java
Familiar

Used in projects, not my first pick.

  • C++
Paul Martin McNeill
About

Building from the island of Ireland

I’m Paul, an AI engineer, web developer and data analyst based on the island of Ireland. I build machine learning forecasting tools, web platforms and analytics for water infrastructure, healthcare, accessibility and day-to-day operations.

My current work is a leakage forecasting and planning platform for a UK water utility, covering more than 1,250 district metered areas. Alongside it I run reproducible research on public data, and earlier work includes an AI-enhanced care-management app built on synthetic data and AI accessibility tools such as a predictive AAC app for non-verbal users.

I’m studying for an MSc in Artificial Intelligence at Queen’s University Belfast (due 2027) and hold a First-Class BSc (Hons) in Computer Science from The Open University. I’ve also completed the Open University’s postgraduate M816 Data Management module.

Currently learning
  • Multi-Agent Systems with CrewAI experimenting
  • Kubernetes for ML Workloads learning
  • Vector databases & retrieval at scale learning
Let's Talk
Credentials

Certifications & memberships

  • Google Cloud Professional ML Engineer

    Google Cloud Professional ML Engineer

    Google Cloud · 2024; recertifying Dec 2026

  • AWS Certified Machine Learning — Specialty

    AWS Certified Machine Learning — Specialty

    Amazon Web Services · 2025

  • TensorFlow Developer

    TensorFlow Developer

    DeepLearning.AI / Coursera · 2024

  • PCPP1 and PCPP2 — Certified Professional in Python

    PCPP1 and PCPP2 — Certified Professional in Python

    Python Institute · 2024

  • MBCS — Member of the BCS

    MBCS — Member of the BCS

    British Computer Society

  • IET Member

    IET Member

    Institution of Engineering & Technology

Trajectory

A working career

Explore my roles, completed studies and professional certifications.

2024 — Present

Volunteer

Digital Volunteer / Technology Advisor

RSPB Rathlin Island Project

2024 — Present
Role

Digital Solutions Developer & AI Consultant

Consultancy contract with a UK water utility

2025 — Present
Role

Creative Director / Technical Lead

Paramount Perceptions (Self-Employed)

2019 — Present
Education

MSc Artificial Intelligence

Queen’s University Belfast

Expected 2027
Education

M816 Data Management

The Open University

2026
Certification

AWS Certified Machine Learning — Specialty

Amazon Web Services

2025
Education

BSc (Hons) Computer Science — First-Class Honours

The Open University

2025
Certification

TensorFlow Developer

DeepLearning.AI / Coursera

2024
Certification

PCPP1 and PCPP2 — Certified Professional in Python

Python Institute

2024
Certification

Google Cloud Professional ML Engineer

Google Cloud

2024; recertifying Dec 2026

2016 — 2018

Role

CRM Systems Coordinator

Industrial Temps

2018 — 2019
Role

IT & Database Systems Manager

Platinum Support & Care Services Ltd

2016 — 2018

Earlier

Education

EDI Level 3 Diploma in Business & Administration

2014
Role

Earlier roles

Various

Up to 2016

Professional memberships & certifications

MBCS — Member of the BCS British Computer Society
IET Member Institution of Engineering & Technology
What People Say

Words from collaborators

Paul took our domiciliary care reporting from scattered Excel files and manual processes to a fully automated Power BI suite. What used to take the team days now takes minutes. He understood the clinical context, not just the data — that's rare.
Dr. Claire HendronService Manager, Domiciliary CareNorthern Health & Social Care Trust
We needed someone who could handle the full picture — data modelling, ETL pipelines, DAX, and the front-end dashboards — and explain it all to non-technical stakeholders. Paul delivered on every front.
Gareth MurrayHead of Digital ServicesNHSCT
The AAC app Paul built changed how we think about assistive technology. The AI prediction engine was fast, accurate, and most importantly, the families found it intuitive. That last part is the hardest to get right.
Dr. Aisling O'KaneSpeech & Language TherapistHSC Northern Ireland
Get in touch

Have something worth building?

Currently open to AI engineering, ML, and full-stack web opportunities — full-time, contract, or freelance. Tell me about the role or project, what you need built and your timeline.