Writing
Insights
Notes from actually building this stuff: what AI implementation looks like in practice, where automation pays for itself, and the architecture decisions that decide whether either one survives contact with a real business.
What it takes to put an AI agent into production
An agent demo is a weekend. An agent with real tool access, running unattended against your systems, is a distributed system with a non-deterministic component in the middle of it.
Nobody’s RAG system fails at the model. It fails at retrieval.
Wiring up retrieval-augmented generation takes an afternoon. Making it return good answers is the actual project — and almost all of that work happens before the model is involved.
Five questions to ask before any AI project
Most of what gets pitched as an AI project is an integration problem, a process problem or a data problem wearing a costume. Here is how I tell the difference before anybody writes code.
How to use LLMs to reduce call centre load
Revolutionize Your Contact Center: How LLMs Slash Call Volume and Boost Efficiency Is your call center drowning in a relentless tide of routine inquiries? Are your valuable agents stuck resetting passwords and…
The role of distributed computing in Generative AI and Agentic AI
The Distributed Engine Powering Generative and Agentic AI The explosive capabilities of modern AI—from crafting human-like text to orchestrating autonomous agents—are not the product of a single, super-powered computer. They are the…
Advanced Distributed Databases for e-commerce
The Backbone of Modern E-Commerce: Why Distributed Databases Are Non-Negotiable Imagine a shopper adding the last high-demand item to their cart, only for the checkout to fail because the inventory count was…
The offer
A free AI & automation opportunity review.
You do not need another generic AI strategy document. I look at how your business currently works and come back with practical opportunities where AI, automation, integration or better architecture would reduce manual work and create measurable value — including the ones I would tell you not to bother with.
Two minutes to request. The written map is yours whether or not you hire me, and there is no follow-up sequence.
- 01UnderstandYour current workflow, tools, systems and where things get stuck.
- 02IdentifyRepetitive work, manual handoffs, disconnected systems, AI-shaped problems.
- 03PrioritiseSeparating interesting ideas from the things that would move the business.
- 04RecommendPractical opportunities ranked by impact, complexity and likely return.
- 05ImplementIf you want it built, I design and build it. If not, the map is still yours.