AI Help For Your Business
I build simple, working AI tools that take over the slow, repeated tasks eating up your day — so you and your team can spend that time actually solving problems.
What I Do
I start with your problem, not with the technology.
Multi-agent platforms built with LangGraph that route natural-language requests to the right specialist agent — RAG, SQL, or task automation — turning manual lookups that took minutes into answers in seconds.
Production retrieval pipelines using hybrid search (BM25 + pgvector embeddings) with reranking — evaluated with RAGAS so retrieval quality is measured, not assumed.
Hybrid collaborative + content-based recommendation engines served through low-latency FastAPI and Redis architectures, validated with structured A/B tests before rollout.
WebSocket, token-streaming assistants with confidence-based escalation to a human — backed by Kafka pipelines processing thousands of events per minute.
Deployments across AWS and GCP with Docker, Kubernetes, and Terraform — backed by CI/CD pipelines with automated evaluation gates, so a regressed model never reaches production.
Analysis and dashboards (SQL, Power BI, Tableau) that turn operational data into the specific intervention that moves the metric you actually care about.
My Work
A few examples of what I've built — with the real results, not just marketing talk.
A six-layer Text-to-SQL architecture — input processing, prompt engineering, LLM generation, execution, validation/repair, and output generation — with an iterative, execution-driven repair loop. Improved on the no-repair baseline by 20.8 percentage points across 1,034 questions and 20 databases, beating the referenced STRUG result.
A FastAPI service wrapping Google's Gemini API with input screening for prompt injection and jailbreak patterns, plus output validation to catch unsafe, empty, or leaked-secret content — with structured allow/block decisions and category codes.
Collaborative + content-based filtering serving 50,000+ monthly active users at p95 latency below 120ms. Validated with a structured four-week, 10% holdout A/B test, then deployed on Kubernetes with Terraform-managed infrastructure and CI/CD evaluation gates.
Analysed 5,000+ diabetes clinic appointment records to identify the key drivers of missed appointments — age, rurality, deprivation, and appointment type — and built Power BI dashboards that shaped a targeted SMS-reminder intervention.
Method
Understand the workflow, the data, and the actual business metric we're trying to move.
Architect the simplest system that solves the problem — not the trendiest one.
Ship working software in short, visible iterations you can react to early.
Production infrastructure with CI/CD, monitoring, and evaluation gates from day one.
Iterate against real usage data after launch — not assumptions from before it.
Get started
My clients use AI to automate the everyday work in their business — answering questions, finding information, handling repeat tasks — so their team can spend time on bigger things. Book fifteen minutes, or just submit your problem below: I read every message myself, and I'll get back to you with a solution within one business day.
Fifteen minutes, no obligation. I'll tell you honestly whether AI is the right fix for what you're dealing with.
Book a callTell me what's slow, manual, or eating up your team's time — I'll get back to you with how AI can fix it.
Thanks — I've got it and will get back to you within one business day.
About
I'm an AI engineer based in the UK with 4+ years building production AI and machine learning systems — from LLM-powered agents to recommendation engines serving tens of thousands of users. I hold an MSc in Artificial Intelligence from Cardiff University, where my research on LLM-powered Text-to-SQL systems and automated query repair achieved 83.8% exact-match accuracy on the Spider 1.0 benchmark.
Through VirtueAI, I work directly with businesses to design, build, and deploy AI systems that solve a specific operational problem — not proofs of concept that never make it past a demo.
Direct contact
Email, call, or find the work itself — whichever's easiest.