Essays on cloud economics, AI infrastructure, edge and governance — 32 pieces since 2020, here and wherever else they ran.
The largest inference saving is rarely a cheaper model. It is sending each request to the smallest model that can answer it well, and governing that routing decision as a platform control with an owner and an evaluation set.
8 min audio
Many AI requests are process-ownership and decision-rights problems that arrive as tool requests. A five-question test to run before funding one, and where to route a request that fails it.
20 min audio
An AI agent can act with or without a human in the loop. That needs more than a credential: a named sponsor, bounded mandate, scoped permissions, explicit autonomy and an evidence trail that survives an incident review.
11 min audio
AI changes the job of an internal developer platform. Model access, data context, evaluation, agent runtime, cost attribution and policy now need a supported path, not six teams inventing six different stacks.
5 min audio
A practical scorecard for prioritising technical debt by interest rate, change frequency, blast radius, remaining life and cost of repair.
4 min audio
A practical cloud-exit readiness framework covering workload fit, dependencies, data gravity, contracts, operations, continuity and phased migration.
5 min audio
A measurement framework for internal platforms: adoption, golden paths, delivery friction, service health, developer trust and cost to serve.
6 min audio
A practical architecture for agent guardrails: task boundaries, permissions, approvals, budgets, evaluation, observability and incident response.
5 min audio
The practical AI FinOps metrics that connect token, GPU, retrieval and agent cost to accountable operational and business decisions.
7 min audio
A practical control map for deploying Model Context Protocol safely: identity, permissions, supply chain, approval gates, logging and operational ownership.
5 min audio
Strengths frameworks sell the upside and bury the cost. Every strength is a default, and defaults misfire under load — here's how to read your results for the failure modes, not the flattery.
19 min audio
AI governance fails when it is a policy without decision rights. A practical operating model for governed AI delivery: lifecycle gates, accountable roles and what you run after go-live.
18 min audio
A local model region answers one question about location. Sovereign AI also requires control of prompts, embeddings, model provenance, operations, jurisdiction and a tested exit path when conditions change.
7 min audio
The Digitalisation World interview covered the AI Grid concept in eight minutes. Here's what that format couldn't fit: the three questions I get asked most often afterwards, and why the answers matter more than the headline.
10 min audio
Traditional cloud bills scale with traffic. AI bills scale with autonomy — and an agent stuck in a loop spends like an intern with a corporate credit card. The circuit breakers, caching, and chargeback discipline that keep agentic spend answerable to somebody.
6 min audio
Training built the centralised AI factory. Inference is quietly un-building it — because serving predictions to users is a latency, geography, and cost problem the industry already solved once, for content, twenty-five years ago.
7 min audio
Most people use "quantisation" and "compression" interchangeably. They aren't the same thing — and knowing the difference is what separates a deliberate self-hosting strategy from cargo-culting whatever ran on someone's laptop last week.
5 min audio
Streaming solved access and then broke it again — eight services, $1,100 a year, and a discovery experience worse than cable. The platforms that survive won't be the ones that spent the most on content. They'll be the ones that removed the friction.
8 min audio
The repatriation conversation has become tribal — cloud believers vs data-centre revivalists. Both camps are wrong. The right question is workload-by-workload: where do the economics, performance, and compliance of this specific system land?
14 min audio
MCP standardises how LLM apps call tools, moving integration from M×N towards M+N. It does not make a connection safe — identity, scopes and review stay yours.
6 min audio
Authentication was the part the industry solved. Agents break everything downstream of it — what the caller intends, how far its credential reaches, and how much it can destroy before anyone notices.
7 min audio
A principle that cannot point to the moment it says no is a preference. What separates governance from a PDF: controls in the delivery path, a data layer you can actually see into, and gates priced by reversibility.
8 min audio
Why the build-vs-buy decision is never binary, how to think about total cost of ownership, and the hybrid approach that actually works in practice.
10 min audio
API inference wins until about 25,000 queries a day — where $12,000 a month of self-hosted capacity meets $0.016 a query. Most workloads end up hybrid.
15 min audio
A decision guide to agentic architecture patterns — single vs multi-agent, sequential, routing, parallelisation, orchestrator-workers, evaluator-optimiser, and reflection — with trade-offs, failure modes, and the observability you can't ship without.
AI Journal
How hyperscaler pricing models and data egress fees constrain innovation, and why portable architectures, distributed systems, and open ecosystems are the way forward.
Techstrong IT
Why cloud cost depends on architecture and workload shape rather than scale, and how distributed models outperform hyperscale for AI-driven, data-gravity-bound workloads.
5 min audio
How organisations across Europe, the Middle East, and Africa balance innovation with economic constraints through AI, edge computing, and distributed architectures.
5 min audio
How Progressive Web Apps leverage distributed and edge cloud services for faster load times, offline resilience, and improved user experiences.
TechRadar Pro
Comparing serverless and serverful computing paradigms — the trade-offs between simplicity and cost versus control and customisation.
5 min audio
A guide to business proposal types — RFP, RFQ, IFB, RFI — and their role in procurement, with a focus on customer value and clear communication.
9 min audio
Windows is the last host in most estates with its own remote-access story. OpenSSH removes the exception — one transport, one key model, one audit trail — and key distribution, not the transport, is the actual project.