Chris Pont

Chris Pont

Create Halo Tickets and Opportunities directly in Outlook

Create Halo Tickets and Opportunities directly in Outlook

Email is where most service and sales conversations begin, but too often teams still have to manually copy information into Halo afterwards. At IJYI, we have been using Halo for around 5 to 6 years, so we have seen first-hand how powerful it is in day-to-day operations. As our use

Turning a New HaloPSA Opportunity into AI Sales Intelligence in Seconds

Turning a New HaloPSA Opportunity into AI Sales Intelligence in Seconds

I remember back when we started IJYI how much time I used to spend fleshing out lead and opportunity data in our CRM tool - Microsoft Dynamics at the time. Researching companies, understanding their likely pain points, checking financials and identifying key stakeholders was important. It meant we had better

Scan Paper Documents into Searchable AI Data with n8n, Ollama and Postgres

Scan Paper Documents into Searchable AI Data with n8n, Ollama and Postgres

In this video I walk through a local AI workflow that takes a scanned document image, extracts the text, identifies the document type, pulls out structured data, stores embeddings in Postgres, and makes the result searchable through Open WebUI. This is a practical proof of concept for businesses dealing with

Building a hyper-local AI for Ipswich

Building a hyper-local AI for Ipswich

A lot of AI is presented as if the model itself is the product. In reality, the value often comes from the underlying data, how it is prepared, and how effectively the system retrieves the right information at the right time. That’s what I’ve been building with a

Why I Built My Own Local AI Workstation

Why I Built My Own Local AI Workstation

Over the past couple of years AI has gone from an interesting research topic to something that is beginning to reshape how software is written, how businesses operate, and how knowledge work happens. Most people interact with AI through cloud services such as ChatGPT, Claude or Gemini. They are incredibly

I built a Xero AI chat agent inside Copilot and Teams using Copilot Studio

I built a Xero AI chat agent inside Copilot and Teams using Copilot Studio

Most small businesses already have the data they need to spot financial problems early. The issue is that nobody has time to constantly review invoices, suppliers, and payment patterns looking for anomalies. So I built a small experiment. An AI agent that connects to Xero and monitors invoice activity, highlighting

Living With a Local-First AI Agent

Living With a Local-First AI Agent

There’s been a lot of noise lately around “local” AI agents. Mac Minis everywhere. Always-on assistants running quietly in the background. Demos that make it look like you’ve basically built your own personal AI sidekick. There’s also been a lot of confusion. Different names for what seems

Making Production Systems Understandable - Lessons from Using Application Insights

Making Production Systems Understandable - Lessons from Using Application Insights

Most production issues aren’t hard to fix. They’re hard to understand. I’ve seen plenty of incidents where there was no shortage of data. Logs were flowing, metrics were charted, alerts were firing. And yet the first hour was spent guessing. What changed? Where did it start? Is

What is an MCP Server?

What is an MCP Server?

Within the world of AI, there's lots of hype around MCP Servers. What are they and why should you care? MCP stands for Model Context Protocol and to understand why this is important, we first need to understand how we got here. In the early days of LLMs