<feed xmlns="http://www.w3.org/2005/Atom"> <id>https://akingscote.co.uk/</id><title>akingscote</title><subtitle>Personal blog showcasing some things i find interesting</subtitle> <updated>2026-02-10T19:06:06+00:00</updated> <author> <name>Ashley Kingscote</name> <uri>https://akingscote.co.uk/</uri> </author><link rel="self" type="application/atom+xml" href="https://akingscote.co.uk/feed.xml"/><link rel="alternate" type="text/html" hreflang="en" href="https://akingscote.co.uk/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2026 Ashley Kingscote </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>Me vs LLMs - Designing a temporary email service</title><link href="https://akingscote.co.uk/posts/me-vs-llms-designing-a-temp-email-service/" rel="alternate" type="text/html" title="Me vs LLMs - Designing a temporary email service" /><published>2026-02-10T00:00:00+00:00</published> <updated>2026-02-10T15:58:08+00:00</updated> <id>https://akingscote.co.uk/posts/me-vs-llms-designing-a-temp-email-service/</id> <content src="https://akingscote.co.uk/posts/me-vs-llms-designing-a-temp-email-service/" /> <author> <name>Ashley Kingscote</name> </author> <category term="security" /> <category term="ai" /> <summary> Don’t worry! This isn’t actually a 75 minute read! It includes a bunch of LLM output. The other week, I posted the article Where’s the moat?. The intention was to capture my feelings around the use of LLMs in the industry at the moment. Since that post, I feel very vindicated. Many others are sharing similar sentiments, and HackerRank shared something eerily similar to my own observations ... </summary> </entry> <entry><title>Where's the moat?</title><link href="https://akingscote.co.uk/posts/wheres-the-moat/" rel="alternate" type="text/html" title="Where&amp;apos;s the moat?" /><published>2026-02-07T00:00:00+00:00</published> <updated>2026-02-09T17:03:48+00:00</updated> <id>https://akingscote.co.uk/posts/wheres-the-moat/</id> <content src="https://akingscote.co.uk/posts/wheres-the-moat/" /> <author> <name>Ashley Kingscote</name> </author> <category term="security" /> <category term="ai" /> <summary> This post documents my observations and experiences regarding the current state of the tech industry, specifically the quality of LLMs and their adoption. I know a few of my peers feel the same, and I’d like to try to articulate why so many of us are feeling hyper-aware of the world changing beneath our feet. These are tangible observations that have made me (and others) realise this is somethi... </summary> </entry> <entry><title>PII Anonymization Service</title><link href="https://akingscote.co.uk/posts/pii-anonymizer-service/" rel="alternate" type="text/html" title="PII Anonymization Service" /><published>2026-01-30T00:00:00+00:00</published> <updated>2026-02-01T17:07:34+00:00</updated> <id>https://akingscote.co.uk/posts/pii-anonymizer-service/</id> <content src="https://akingscote.co.uk/posts/pii-anonymizer-service/" /> <author> <name>Ashley Kingscote</name> </author> <category term="cloud" /> <category term="security" /> <category term="azure" /> <category term="microsoft" /> <category term="ai" /> <summary> I had an idea for a PII anonymization service, with the intention of maintaining integrity with the data it’s anonymized. The original context was for anonymizing Microsoft Sentinel database dumps, so that I can re-use the data for threat hunting training, without exposing real-users PII. But to maintain integrity and realism, the concept grows in complexity. I can’t substitute a private IP a... </summary> </entry> <entry><title>Three different LLM Guardrails, and integration with Strands Agents (AWS)</title><link href="https://akingscote.co.uk/posts/aws-strands-agents-guardrail-integration/" rel="alternate" type="text/html" title="Three different LLM Guardrails, and integration with Strands Agents (AWS)" /><published>2025-10-04T00:00:00+01:00</published> <updated>2025-10-04T11:16:00+01:00</updated> <id>https://akingscote.co.uk/posts/aws-strands-agents-guardrail-integration/</id> <content src="https://akingscote.co.uk/posts/aws-strands-agents-guardrail-integration/" /> <author> <name>Ashley Kingscote</name> </author> <category term="cloud" /> <category term="security" /> <category term="aws" /> <category term="ai" /> <summary> Summary This blog post explores three AI guardrail products, and how to integrate them with the Strands Agents SDK. I opened a pull request into the Strands Agents Samples repo two months ago, and havent seen any updates on it, so have decided to just share the writeup anyway. System-Level Safety Meta’s responsible use guide (for AI) essentially categorises inputs and outputs into an LLM model... </summary> </entry> <entry><title>Microsoft Azure Nested Virtualization: Creating on-premise Windows Domain environments</title><link href="https://akingscote.co.uk/posts/azure-nested-virtualization-on-prem/" rel="alternate" type="text/html" title="Microsoft Azure Nested Virtualization: Creating on-premise Windows Domain environments" /><published>2025-08-04T00:00:00+01:00</published> <updated>2025-08-04T18:16:49+01:00</updated> <id>https://akingscote.co.uk/posts/azure-nested-virtualization-on-prem/</id> <content src="https://akingscote.co.uk/posts/azure-nested-virtualization-on-prem/" /> <author> <name>Ashley Kingscote</name> </author> <category term="cloud" /> <category term="security" /> <category term="azure" /> <summary> Summary Modern Microsoft Azure hypervisors support nested virtualization; meaning you can run virtual machines within virtual machines. With a bit of magic, you can create an effective “Virtual ESXi” server and run a few virtual machines from ISO files, which is much closer to an on-premise environment. However, instead of ISOs, if I have a few existing Virtual Hard Disks (VHDs) that are confi... </summary> </entry> </feed>
