Ai worth a look

 Googles - Agent Development Kit

Enable AI assistance with Azure DevOps MCP Server

Microsoft Foundry

Railway Infrastructure - Signalling

Understanding Railways Series:

UK Railway Industry for Dummies, focusing on Rail Infrastructure

Railway Infrastructure - Signalling (this post)

  Signalling for Railways 

Historically, trains were operated by a driver who knew a lot about the train, the route, and even the train itself.  Speed, signalling, and braking distance were controlled by the driver, and they had to manage the train, the driving, and the route information affecting them.  Signalling was used to help the driver determine whether the rail line was clear or approaching, when to slow down, and to provide reminders, thereby allowing the driver to control the train safely by managing multiple factors.

Advancements in technology have built on existing infrastructure and approaches, enabling more trains, safer travel, and better information.  For example, wheel counters allowed signalling to ensure that a train and all its wheels have cleared a section.

Telecommunications allow a central control centre (ROC) to communicate with the drivers.  GSM-R...

The train should run regardless of temporary telecommunications issues or unavailability (assuming it is safe).  The onboard computer on every train can provide the driver with information or act on it, such as automatically stopping the train if a red light is detected while the train is on the section of track the driver is entering.  

ETCS is for modern signalling; the fundamental principle is that all trains, routes and tracks can be managed centrally safely (see SIL4).  Everything on the railway has to be safe.  Super safe, if unsure, stop is the principle.

Common Equipment

Balise

A balise is a device mounted on the track between the two rails that sends messages to a train as it passes overhead, primarily conveying the train's position.

Understanding Railways Series:

UK Railway Industry for Dummies, focusing on Rail Infrastructure

Railway Infrastructure - Signalling (this post)

GIS Notes

What is GIS?

GIS stands for Geographic Information Systems, which are tools and techniques for capturing, managing, storing, processing, and analysing spatial data. It is part of the broader geospatial technology ecosystem, which also includes drones, remote sensing, and GPS.

Geospatial data (Raw)

Definition: Any data that includes a geographic component, describing the location and attributes of features on Earth, contains raw information, like points, lines, and polygons, that has a real-world location associated with it.

Examples: a car's GPS location or a customer's address.

GIS data (Organised)

Definition: Geospatial data that is structured, stored, and analysed using Geographic Information System software.

Examples include a digital map of roads created from GPS data or layers of data showing flood-risk areas.

Summary: Geospatial data is the foundation: the raw material for all things spatial. GIS is a toolset that may include tools like ArcGIS from Esri.

Other:

In the AEC space, building and Asset management rely heavily on GIS within BIM.

ArcGIS is the industry leader in GIS tooling, and comes in three versions: 

• Desktop (ArcPro, Arc Toolbox, ArcCatelog),
• Server (), 
• SaaS ArcGIS Online (AGOL).

 GIS data comes in various formats such as Shapefiles, GeoJSON, KML, or geodatabase feature layers.

What WGS84 and GeoJSON Mean?  

These are the most common formats for storing position (WGS84) and shape data with coordinates (GeoJSON) 

WGS84 (World Geodetic System 1984) is the global standard geographic coordinate reference system. It represents positions on Earth using latitude and longitude in decimal degrees.

GeoJSON is a widely used format for encoding geographic data structures in JSON. According to RFC 7946, all GeoJSON coordinates must use WGS84 (EPSG:4326).

The OSGB/OSGB36 coordinate system, also known as the Ordnance Survey National Grid or British National Grid (BNG), is a geographic grid reference used in Great Britain.  

The European Terrestrial Reference System 1989 (ETRS89).

Standards and formats Notes

ISO 19115: International standard for geographic information metadata.

Shapefiles: Upload as a ZIP archive containing .shp, .shx, and .prj files.

File Geodatabases: Must be compressed into a ZIP file before uploading.

WMS/WMTS Services: Add Web Map Service (WMS) or Web Map Tile Service (WMTS) layers by providing the service URL.

Prefix Conventions

• Points: Use prefix pt_
• Polygons: Use prefix py_
• Lines: Use prefix ln_
• Raster: Use prefix rs_

ESRI Competitors

Esri have ArcGIS, which is the gold standard in GIS. It's pretty expensive if you don't need the feature set offered by AGOL/Esri.  
Google offers easy-to-set-up and use mapping, geo services and APIs Google Maps Platform Pricing   . I'd usually choose this when hardcore analytics are not needed

Common source of data used to mash onto maps

DEFRA,
Environmental Agency, 

Natural England,

Esri Living Atlas,

Open Geospatial Consortium  NB!

GitHub Copilot with Claude Sonnet 4 is amazing, and GPT 5 is even better

I couldn't sleep, so I decided to build a Pulumi C# application that uses an existing MCP Server. My forms will utilise the client to allow me to access my Azure subscriptions and resources - wow.  Build a really cool tool quickly - Claude Sonnet 4 is once again significantly better than GPT-4.1 for programming with GitHub Copilot.

Update Sept 2025: I'm now using GPT-5 over Claude Sonnet with GitHub Copilot when programming in VS Code.  Both feel about the same quality to me.

GitHub have this for comparing AI models for GHCP, which is very useful.

I am using GPT-5-Codex, which "is a version of GPT-5 optimised for agentic coding in Codex".

I am also really liking GitHub Copilot code review

Anthropic's Claud 4.5 is also excellent..

AI for developers and Architects

The cost of prototypes is unbelievably low using AI. 

Rapidly creating a prototype, especially with new or less well-known technology, is where I derive significant benefits from AI.

How to build application prototypes?

1. Write /reverse prompt/Adjust instructions into md file
2. Agentic AI (specialising in Doc Extraction) to extract and refine from md file
3. Run using IDE-based copilot (VS Code with GitHub Copilot) (AmazonQ) (Cursor, Windsurf, Steamlit) 

Thoughts: Developers are adjusting to using Ai to support software solutions.  The developer role will continue the trend of making technical implementation more accessible, allowing knowledgeable IT engineers or domain experts to build faster and better than citizen/amateur developers.  Ai assists in complex decisions!  

What needs to improve?

• Knowledge is key.  AI needs to have narrow expertise at the right time. i.e. only domain knowledge, not influenced by other data.  Quality of input data used to train.  Allows for dynamic reasoning.
• Session/long-term contact agreement/understanding to improve the understanding between your IDE and me.  Remember how I prompt and provide feedback on how I digest information.  Context between the human developer and Ai is Paramount.
• Control of IDE integration with coding copilots, clear return to the user developer to make better decisions.  Context is Paramount.
• Governance & Data (Connectors, API's, code complex processes (MCP maybe), quality of data).

Retrieval Augmentation Generate (RAG)

AI needs to be able to connect to my existing Tool Landscape:
I use Azure, C#, Playwright, and GitLab.  I want my IDE to work with these tools and many more.  MCP servers publish their functionality, and I can connect my Copilot/Agent to use multiple MCP servers.  This is what GHCP does for VS Code, allowing you to add MCP clients dynamically to use existing MCP Servers. 

Model Context Protocol (MCP) MCP is a protocol (created by Anthropic) that allows an MCP client to connect to an MCP server, which in turn provides specialist knowledge. Authentication should use OAuth to secure access. My Applications/Agents use the MCP to ask the MCP Server, 'What can you do?' so they know how to use it.  The MCP server allows you to interact with a system.  It is often referred to as the "Arms and Legs" of AI. The MCP Server, when built, informs the client of its capabilities and then performs actions, such as updates, via an API.   Summary: Use MCP to enable the client to communicate with other resources/tools. NB: An Agent can utilise multiple MCP Servers.

Agents-to-agent (A2A) 

A2A allows agents to work together.  So two agents can leverage each other; the other agent solves the issue and returns the answer for the first agent to use.  Whereas MCP allows any agent to speak to a source.  Agents complete a task and give it back to the calling agent. 

 

Summary: Use A2A to talk to specialised Agents, and the agent returns the calling agent's answers.

Artificial Intelligence as a mega trend

Overview of AI

The world has gone mad for AI.  Constantly, I see overhype and poor messaging leading to a misunderstanding of potential.  

AI is not new; the ability to use it for commercial gain is new at the scale we now have.  AI excels at helping us identify patterns, gather information, and is primarily a decision support system (DSS).

AI is not intelligent, but rather good at making complex decisions, and it has biases that we teach it.

This means AI is useful for specialisation, not a generalisation of "smartness", now that ChatGPT et al. are wide-ranging, people are assuming it is a general-purpose tool.  Actually, ChatGPT is a specialist in breaking down and grouping language based on a data source.  For those in the technology industry, we pretty much know that ChatGPT is a good Google (search engine).  

So, what is AI going to be successful at?  Well, this is my prediction:

AI will have a massive impact on many industries:

1. Healthcare - guess what? More surgeons and people will be needed, not fewer.  Here, I focus on Healthcare examples.  People need to interact with others; avatars are a joke. I can talk to Alexa already.  There is very little to nothing in this space except for snake oil salesmen.  Please prove me wrong! More skilled people are needed.

2. Software Development/IT - This is a significant one.  Programmers' roles will change significantly; those with a good understanding and knowledge will thrive, while those with superficial knowledge and a lack of ability to truly understand and work through challenges will likely disappear.  Technologists will focus on challenging problems and introduce significant improvements to all business processes.  The amount will continue to grow.  There is not a lot of agentic, "smart AI" in the space, and we are 50 years away from this, imo.

3. Manufacturing - it won't make the impact that the media says it will.  We are good at manufacturing.  The sub-functions that will benefit include machine maintenance, sensor usage, and performance/behaviour will change.  This will allow you to improve Machine Maintenance (MM) and scheduling.  Think of railway lines; they need to be shut down, and it costs millions to trim hedges. Imagine now that you know the level crossing "lifty uppy-doowny" box/bar is showing signs of fatigue.  Shift the fix left and save the unscheduled breakdown; the train line and knock-on effects shall result in massive improvement.  We are already proficient in manufacturing and, to some extent, automation. If the AI is not significantly better, it is not worthwhile. More skilled people are needed.  

Machine Maintenance in Manufacturing.  AI is needed to mature MM. 

Techniques such as defect detection are already well-established using Visual AI at the micron level.  Rubbish detection.  Using AI will be beneficial - sure, it will become cheaper and easier to acquire this system capability for less, but AI is merely an enabler, and it has been available for well over a decade.  More skilled people are needed.

4. Service Industry - Robots serving people, please, it's mad, except at MacyD's (McDonald's) and honestly, minimum wage workers are pretty efficient there, and it will be too sterile.  Pushing out patties, well, if you need AI for this, you don't know what AI tries to do.  AI & automation are already in the processing and packaging processes.  The big stuff with AI will be in social media and advertising (and don't get me started there, automated advertising will absolutely fail. We need to invent a missile to destroy non-human posts).  More people will be required in these new and changed services.  

Analogy:
1. Old technology: Hand weaving material was a big profitable business in Britain; along came looms; these workers got upset and broke the looms and ended up in prison or broken; these were the Luddites (who refused to embrace technology).  The Luddites ended up broke, and all this could have been avoided by embracing technology, as they were the most knowledgeable about materials and production. They are the natural experts.   

2. Trend jumpers on: Too many companies wanted to build looms, and a handful of players did brilliantly and still exist today.  Think Microsoft and AWS; they are transitioning from being programming technology companies to AI technology.  They still solve the same problem of process improvement.  The weavers who decided to go into building and repairing looms did exceptionally well, but ultimately ran out of demand, and their prices were driven down as there was an excess of supply.  Still a good change.  Many people also got hurt here. Be careful inventing new technology in processes; you get it right, you are a hero; get it wrong, go find a new job.  Lots of sales silver bullets are being produced.  There are tons of "AI experts", but mostly this is absolute rubbish.  With rare exceptions, you are not an AI expert unless AI was in your job description more than 5 years ago.  Beware the snake oil salesmen, nowadays they come in many forms, sizes and shapes :)

3. Embrace change:  Normal, common-sense (smart) people realised they actually had 4 options:

1. Learn how to use a loom.  Use the technology available and use it to build garments faster;
2. Build looms and support the loom business;
3. Do nothing, continue to offer hand-weaving labour to the market.  So take your pension and hope like hell you win the lottery (I'm still backing this option for myself); or
4. Expert hand craftsmen or women :) Become the best hand weaver in the world, and people pay you for your expertise; these people's descendants/business still exist.  But big surprise: it's hard, it takes a long time, it's unlikely to make you rich.,, So, sure, go do this if you are a genius in your field and love it, but don't die of surprise when you go broke or don't get the return you deserve for all that hard work.

Summary: Embrace technology and AI, it is only a decision support system.  More skilled people are needed, as you have the background, being professional and embracing change means you are more in demand.  Sitting on your backside waiting for the lottery means you are like 90% of people, and you'll get 2 jet skis and a new husband! yipee.

Healthcare

Good Use Case: Diagnostic medicine

Diagnostic medicine has become the centre of healthcare, and the ability to use AI, which is better at detecting abnormalities than the best radiologist using a single trained model, yields results in near real-time.  This means that consultant radiologists and specialists can receive reports in seconds that are of unparalleled quality.  GPs have the best guess within seconds, rather than well... we all know this.

AI also provides probability, so it's easy to prioritise any reporting that's life-threatening to a specialist, allowing them to focus on the most challenging work and receive the in-depth information provided by the AI.  

This is possible because we are dealing with a relatively narrow field of data that we have taught AI to handle. Think of X-rays; the results are far superior to an expensive resource (a Radiologist) that takes at least 12 years to train.  And more to get brilliant.

Should we stop training Radiologists and diagnosticians and allocate our resources to AI?  Absolutely not!!   

Radiologists should be using the AI reports, validating, using the info and extrapolating, when an issue is detected, this must be added back into the learning model resulting in improving the AI.   AI should not act. It must only be used to support.  Acting should be restricted to notifying relying parties such as GPs.  

Good Use case: Online GP Appointments and triage

If you have an issue, you go onto an NHS app that will ask you for your symptoms and ask a few follow-up questions.  It will only give you its best guess (this is already amazing imo.), this in turn, will triage your call into "go to your emergency department, they know you are coming", "let's book you an emergency appointment", or "this is my recommendation, and why".  Dr Google actually becomes useful (weird medical insider joke).  Honestly, we could do so much more, but care is given to the right people, "shift-left" (the sooner you catch it, the cheaper and better the solution, 100% applies to healthcare).

Preventive medicine and nudging technology will have profound improvements in people's lives and lifestyles.  Hooking into ambulance services and driverless automated vehicles,.. people do the hard stuff and make the decisions. AI does the piece efficiently and quickly that we as humans aren't good at. Hopefully, you are understanding the difference between narrow and wide industries.

Bad Examples: Robot Surgery or treatment rooms

Robots replace people in operating theatres. It is insane!! A surgeon could use AI to obtain better diagnostic data more quickly; they could even utilise technology like AI-assisted operations, then send messages if it detects that the actions are not optimal or there is a clear risk that a priority has changed.  It is brilliant for decision support. It's not a good idea to try to automate complex decision-making.

My AI Posts

Copilot Studio 2025 Simple Notes

Artificial Intelligence as a mega trend

Microsoft's Copilots Explained 

Prompt Engineering with Microsoft Copilot 

AI Model Comparison (this post)

Ignite 2023 - Keynotes - big push to AI Summary

This post does not look at Strategy and Purpose

All AI solutions give themselves an exponentially better chance of success, regardless of industry, if they have a strategy, purpose, and FAIR data (Findable, Accessible, Interchangeable/exchangeable, and Reusable).

UK Railway Industry for Dummies focusing on Rail Infrastructure

Understanding Railways Series:

UK Railway Industry for Dummies, focusing on Rail Infrastructure (this post)

Railway Infrastructure - Signalling

Rail assets are organised into large, hierarchical asset classes that are interdependent, forming a rail system. These rail assets are organised using detailed, lower-level assets built from taxonomies and ontologies tailored to each jurisdiction within the rail industry.  Railway interaction and asset operations must comply with stringent rail regulations.  Safety has a massive focus.

Taxonomy organises data hierarchically, while ontology models both hierarchies and complex relationships between entities and their properties. In the rail industry, ontologies are crucial for successful asset modelling.

The picture shows examples of significant assets (high-level)

Main Railway Infrastructure Assets high-level overview.

An AI-generated image to explain commonly used railway terms.

The railways consist of "rolling stock, rail infrastructure, and environment"; these components have multiple relationships with one another.

1. Rolling stock is the trains.

2. Rail Infrastructure relates to: 

    2.1. Electrification/power/energy, generally used for power supply for signalling, train power, and telecoms.  Key protocols for using devices are MQTT, MODBUS and IEC

• UK network supplies at 400kV, and train propulsion uses 25kV (AC) for Mainlines and 1-3kV (DC) for requiring step-down.  Train propulsion power is referred to as Traction Power Supply.
• Non-Traction Power Supply, used for signalling, station power, and lighting
  
  
• Overhead Line Equipment (OLE) is critical in railway electrification.  OLE span - Longer spans reduce the number of masts, lowering installation costs—but only if mechanical and electrical limits are respected.
• Overhead Contact System (OCS) or Third Rail: Transfers power to trains.

    2.2. Telecommunication, track-to-control, and train-to-control are used to communicate, including sensors and IoT devices.

    2.3. Signalling relates to ensuring train safety so the train knows there is a train ahead of it, and issues when to slow down.

    2.4. Track Engineering, also known as Rail Engineering and The Permanent Way, involves the rails, connectivity, support, extensive physics and geometry, steel rail installation and joining, ballast (the ground on which the track is laid), drainage, substructure, and sleepers. It gets detailed with rail joins (Fishplated) and even the welding process used.  Fastening types, baseplates, sleepers, off-track maintenance such as hedge trimming (you won't believe the rules unless you work in the rail industry) ...

SCADA systems integrate sensors, Remote Terminal Units (RTUs), Programmable Logic Controllers (PLCs), and Human-Machine Interfaces (HMIs) to collect real-time data, automate processes, and ensure operational safety and efficiency. In rail, SCADA typically manages traction power, station systems, and communications infrastructure.

3. The environment refers to the existing conditions before the railway, including the topography and type of terrain, bridges, and rivers.

The interdependencies with the rail industry are perfect for numerous AI scenarios.  With any AI, you need high-quality data and must secure it appropriately.  Bring information from across business functions together to enable automation, ML, and AI, and support better decision-making.

Each country or jurisdiction has different rules for trains, and operators must comply with Health, Safety, and Environment (HSE) regulations.  There are industry rules adapted to each jurisdiction, and standards vary by region.  For example, most jurisdictions have a gauge width requirement; in the UK, the standard gauge is 4 feet 8 1/2 inches (1435mm).  There are exceptions, such as heritage railways in the UK.  There are manufacturing standards for everything.  EN13674 is the British Rail specification for the actual pure steel used to manufacture the track to be installed.

ISO 55000/1/2 addresses Physical Asset Management.  Building Information Modelling (BIM) enhances the design and construction process, and both apply to Rail Infrastructure.  There is generally a disconnect between Asset Management and BIM, and the International Foundation Modelling (IFC) aims to establish a standardised asset model for the railway industry; we are on v4.3.

SIL4 - Used for critical safety systems such as railway interlocking control systems. Safety Integrity Level is defined in functional safety standards, such as IEC 61508. SIL1 is the lowest level, and SIL4 is the level at which a system has the lowest likelihood of dangerous failure and the highest reliability. 

Understanding Railways Series:

UK Railway Industry for Dummies, focusing on Rail Infrastructure (this post)

Railway Infrastructure - Signalling

References used: 

Permanent Way Institution (2023) Understanding Track Engineering. London: The PWI. Available at: https://www.thepwi.org/product/understanding-track-engineering/ (Accessed: 4 July 2025)

Camarazo, D., Roxin, A. and Lalou, M. (2024) Railway systems’ ontologies: A literature review and an alignment proposal. 26th International Conference on Information Integration and Web Intelligence (iiWAS2024), Bratislava, Slovakia, December 2024. Available at: https://ube.hal.science/hal-04797679/document (Accessed: 4 July 2025).

Network Rail (2021) Asset Management: Weather Resilience and Climate Change Adaptation Plan. London: Network Rail. Available at: https://www.networkrail.co.uk/wp-content/uploads/2021/11/Asset-Management-WRCCA-Plan.pdf (Accessed: 4 July 2025).