Dynamic Code Blocks

Vertex AI redirection loop accessing Google Console

How to fix the eternal looping of Vertex AI and Google Console.

Microsoft Dynamics GP

Adding a field from a custom table to Dynamics GP report and word template using C#

Extending GP reports using calculated fields and RW functions lets you return custom data (e.g. from SQL or an API) without alternate reports. Use caching to avoid per-line queries for better performance. Word templates need remapping to include new fields.

Microsoft Dynamics GP

"RMA Line is edited by user" locked RMA record in Dynamics GP

Post an RMA receipt in GP’s RMA Receiving window, GP locks the RMA Entry/Edit, even after logout. Only the same user clearing it via RMA Entry can unlock it. This bottlenecks separated warehouse/service workflows.

AI

The Vibe Coding Effect – Client Expectations and the Cost of Custom ERP/Enterprise Development

Vibe coding changes how clients see software — fast, disposable, AI-built apps done in hours. But once they see it, will they ever accept expensive custom dev again?

AI

What is vibe coding, and should enterprise software implementation and support consultants care?

Vibe Coding is the idea of building software without caring about the code. It is about focusing purely on the outcome. Why should you care?

AI

Is it responsible to use AI where simple logic would suffice?

It is too easy to reach for AI when developing modern solutions, but what is the eco-impact of that decision?

Learning AI

Understanding Context Windows in LLMs

Ever wondered why the prompt size is limited when prompting an AI model, or why it seems to forget what it was told earlier in the interactions? Context windows provide working memory to AI.

Learning AI

What is RAG in AI?

RAG helps AI move beyond its training limits by dynamically retrieving relevant information snippets, allowing language models to answer specific questions with precision and context.

Learning AI

Is weight, parameter and tensor interchangeable when talking about LLM model sizes?

Weight, parameter and tensor are used when talking about LLM model sizes, are they all the same thing?

Learning AI

SMALL but mighty models is where it is at

Small AI models are cost-effective, fast, and ideal for business tasks. Cheaper to train and run, they work locally, offline, or in IoT devices, ensuring efficiency and compliance. With less energy use and fine-tuning options, they prove that smaller, task-focused AI can deliver big results.

Learning AI

Local hosted models

It is fun to download Ollama and run an AI model locally on your laptop or desktop computer, even without an Internet connection. It teaches us to think about model selection even in cloud AI.

AI

Paradigm shift from Search engines to Answer engines & Perplexity

Is traditional search dead, users are trying answer engines that give great results but with increasing toll on the environment.

Learning AI

Logic of thought prompting

Logic of thought prompting is a technique used to force the AI out of speedy responses and in to making a more considered answer with significantly more thought and detail.

Learning AI

Riding the "S" curve of AI growth

Academic and business growth of AI and recent news on Amazon giving academics more compute.

Learning AI

Understanding Openness in Language Models: Open Source, Open Weights, and Restricted Weights

Open weight models vs open source models, they are often confused when people discuss AI models.

Learning AI

What are AI Guardrails & Responsible AI?

Guardrails facilitate responsible AI, guiding users to good results from AI and putting a barrier up to prevent harm. Guardrails are the safety barrier used by AI systems to ensure the system remain on target for their intended use and do not cause harm.

Learning AI

What are AI prompts and what is prompt engineering?

By learning prompt techniques, you gain the ability to tailor AI outputs to your specific needs, making interactions with AI more productive, whether you're brainstorming ideas, generating content, analysing data, or seeking insights.

Learning AI

What is Agentive AI, Agentic AI and AI Agents?

AI Agents, Agentic AI, Agentive AI, AI Assistant, CoPilots are all terms we see around business automation. All relate to using AI to help accomplish tasks but with varying amounts of human intervention and drive.

Learning AI

Understanding Large Language Models: The Core of Today's Generative AI Boom

Having a model in your head when working with generative AI and LLM platforms is a great help. This posts paints an overview of AI models and introduces common terms every new comer to AI platforms encounters.

Learning AI

Zero-shot Multi-Shot prompting

0-Shot, 1-Shot, 2-Shot, 3-Shot, 4-Shot, 5-Shot are all a way of prompt engineering, using examples to shape the response from an LLM.

Learning AI

What are the Differences Between Instruct, Chat, and Chat-Instruct Models in LLMs?

When downloading or selecting models, you will see them named instruct, chat, chat-instruct models, what are they and what are the differences?

AI

Technology Adoption Lifecycle & "Crossing the Chasm" with AI in 2024

How come customers and product are at a disconnect?

Security

Enhancing Email Security with SimpleLogin

Keep blogs updated and your readers will love you more, get more visits too.

Microsoft Dynamics GP

Handling SOP Document Number Chaos: A Dynamic SQL Solution

When the sales document numbering in Dynamics GP went off track, I used dynamic SQL and eConnect to renumber 20 orders across 120 tables. This post details the problem, solution, and includes a helpful SQL script for correcting document numbers efficiently.

SQL Server

SSMS Activity Monitor Pausing and Processor Time greyed out disabled

Fix to SSMS Activity Monitor pausing.