Yep. If the UK is anything like Australia, they will have a small army of contractors who specialise in building SQL databases for various important and pointless requirements for the government. These contractors are used to working on giant, sensitive data, databases with insufficient allocated time. It should have been pretty much trivial for the UK govt to solve this.
And yet, I have first-hand witnessed a scenario like the one described in an AU government department. A small system developed by business (one person who had subsequently moved on) using Excel and Word and macros to keep track of information and generate letters to "customers" had become an essential tool, but unsupported and undocumented. When we (IT) recommended redeveloping it in Java with an SQL database (and documentation and testing and backups), they balked at the cost. Partly because the original person did the work "in their spare time", so the business never saw the actual costs. And partly because there are zero infrastructure costs with Excel and Word. There was very much a feeling that IT massively inflate the costs and will build a Rolls Royce when a Ford will do. It was a house of straw vs house of bricks situation, but they were happy with their straw house, they thought their only problem was that the little pig who built it was no longer there.
The problem with my Private sector Australian company is everything IT related is aggressively outsourced through various networks of contractors.
In the old days when the relevant business application was written, hosted and supported in house there was a clear chain of responsibility I could pick up the phone and I'd have a direct line to the person who "owned" the application.
Nowadays if there is a problem it's pick up the phone talk to helpdesk get assigned a ticket number and get the buck passed between different teams, The database team will blame the server team, server team will blame the networking team, networking team will reply to ticket with 'looks ok no problem on my end' and the ticket will get closed without resolution.
From what I can tell there are a bunch of incentives in the support contract around how quickly support can close out tickets, so rather than trying to fix the problem support try to do everything they can to farm the ticket off to someone else so it won't impact their metrics. The whole thing feels maddening and has to be rather inefficient.
Victoria (Australia), until a few weeks ago, did contact tracing via hand-written notes and faxes. Sure, it's not going to overflow at 16,000-odd cases, and doesn't require a DB admin and test cases, and all of that. But it performs at a fraction of the speed, and is one of the major reasons the second wave here got out of hand. Just because that army of contractors exists doesn't mean the relevant departments know of it's existence, or decide to use it.
I'm pretty sure the UK does have actual software with actual databases backing up test and trace, some of which was outsourced - in fact it looks like our opposition party and opposition media are trying to blame this failure on outsourcing, even though that has no foundation in reality, mostly because this plays well with their supporters for reasons too tedious and political to explain. Unfortunately, this happened at a kind of interface between different systems designed to take in results from both the Pillar 1 NHS testing and Pillar 2 Lighthouse testing for the general public, deduplicate them, and spit them out to the contact tracing system and the government dashboard. These are seperate systems run by seperate organisations for various not-so-interesting reasons to do with the structure of the healthcare system and the history of Covid testing in the UK.
