Portrait of Bryan Small
Applied AI Builder & Scottish AI Analyst

I build, test and track AI from Perth, Scotland.

The objective is not to sound authoritative. It is to publish enough useful evidence that authority becomes a consequence.

Operating philosophy

Build. Test. Explain. Track.

My mission is to become the trusted practical source for AI implementation, intelligence and analysis in Scotland — through useful tools, evidence, research and working builds. No manufactured certainty, no self-declared authority.

01
BUILD
02
TEST
03
EXPLAIN
04
TRACK
Working builds

What I build

ShieldedID

Zero-knowledge identity protocol. Bulletproofs ZK in WASM, pairwise subject IDs, zero PII storage. Open source.

STCL

Semantic Token Compression Layer. Provider-agnostic pre-inference compression, ~38% average token cut. Open source.

UnitedLines

Encrypted social network. Privacy-preserving communication as a working build.

Résumé & capabilities

What I can build

Hands-on applied AI and full-stack engineering. I build working systems end-to-end — from local LLM orchestration to production web apps on the Cloudflare free tier — and I publish the method, cost and failure modes.

Core capabilities

Applied AI & LLM systems

Local LLM orchestration (Ollama), model selection, prompt engineering, RAG and vector retrieval, agent workflows, semantic compression. I build AI that runs on your own hardware — no vendor lock-in.

Full-stack web & WebGL

Static-first sites on Cloudflare Pages, serverless Functions, Three.js/WebGL immersive scenes, progressive enhancement, SEO, accessibility and performance budgets. This site and the Observatory are built this way.

Automation & data pipelines

n8n workflows, scheduled cron jobs, data ingestion and ETL, vector databases (Chroma), Redis, email automation via SMTP, analytics and conversion tracking. Systems that run themselves.

Privacy-preserving engineering

Zero-knowledge proofs (Bulletproofs in WASM), pairwise identifiers, zero-PII storage, encrypted communication. Built around the principle that privacy is a design requirement, not an add-on.

Technical stack
Python JavaScript / TypeScript Three.js / WebGL HTML / CSS Cloudflare Pages + Workers Serverless Functions Ollama / local LLMs RAG / vector search Chroma / vector DB Redis Docker n8n automation Git / CI SMTP / email delivery Turnstile / bot protection Zero-knowledge proofs WASM OSINT tooling Data pipelines Scheduled automation
Working builds

ShieldedID

Zero-knowledge identity protocol. Bulletproofs ZK in WASM, pairwise subject IDs, zero PII storage. v1.5.0, Apache 2.0, open source.

STCL

Semantic Token Compression Layer. Provider-agnostic pre-inference compression, ~38.2% average token cut (up to 59.4%), ~3.5ms overhead. MIT, open source.

Scotland AI Observatory

Independent evidence-led observatory: 10 national AI commitments tracked, adoption index, SME diagnostic, lead capture. Live on Cloudflare Pages.

Digital products

Practical AI workbooks and toolkits I publish on Etsy (TechBlueprints) — the same evidence-led approach, packaged for everyday use.

ChatGPT AI Workbook

120 prompts, workflow planner, tracker and offline tool. Turns ChatGPT into useful, verified work — not random prompt collecting.

View on Etsy →

Claude AI Workbook

120 prompts, artifact and cowork planner, tracker, offline tool. A repeatable system for turning Claude into useful, verified work.

View on Etsy →

OpenClaw AI Workbook

Secure setup, agents, automation, 120 prompts and offline planner. A repeatable system for turning OpenClaw into useful, verified work.

View on Etsy →

AI Safety & Ethics Guide

33-page field guide turning major AI safety and ethics frameworks into everyday practice — clearer boundaries, better verification, stronger human oversight.

View on Etsy →

AI Voice & Deepfake Detection Toolkit

Offline toolkit for assessing suspicious voice calls, audio clips and possible voice-cloning scams — triage dashboard, waveform review and case log.

View on Etsy →
How I work

Evidence over claims

Every build publishes the problem, baseline, stack, time, cost, result and failure modes.

No manufactured certainty

I test claims, including my own, and report limitations honestly.

Zero-outlay by default

I build on free tiers and local hardware first, and only spend when a system earns it.

Independent observatory

Track what Scotland promises. Measure what it delivers.

I run an independent, evidence-led observatory for Scottish AI: national strategy delivery, adoption data and public-sector progress. All 10 commitments in Scotland's AI Strategy are tracked against observable evidence with sources and dates.

Let's build something useful.

Whether you want to start an AI pilot, propose a build, or discuss Scottish AI intelligence — tell me the problem you're trying to solve.