AI-powered predictive maintenance has been on the radar for years, but for most facilities, it still hasn’t fully landed.
Chris sits down remotely with Colin Morris, Senior Director of Solution Consulting at MaintainX, the AI-powered maintenance and asset management platform built for the industrial frontline. Colin has spent eight years working in this space, long enough to have watched maintenance shift from an afterthought to a strategic asset across North American manufacturing.
They cover the real barriers to AI adoption in maintenance: unstructured data sitting across disconnected systems, outdated assumptions about what predictive tools should deliver, and the foundational steps most facilities skip before they’re ready.
Colin walks through what parts data to collect and why, how maintenance has evolved from cost center to cost saver, and where agentic AI is taking the industry next, including what scheduling looks like when an agent does the first pass and a human approves the plan.
Subscribe
Apple | Google Podcasts | Spotify | Stitcher | YouTube
3 Quick Things from this Episode
- A predictive maintenance system that shows no faults is not failing, it may be succeeding. When equipment runs well and maintenance happens at the right cadence, there is nothing for the system to flag. Many teams expect constant output and interpret silence as a sign something is wrong with the tool. The absence of alerts is often the point.
- Voice technology is becoming one of the most practical ways to capture knowledge before it walks out the door with retiring workers. Rather than asking experienced technicians to type out observations at a terminal, voice transcription lets them summarize a completed job in under 30 seconds. That data gets added to a knowledge base, meaning a 25-year veteran’s methods are accessible to someone who joined two years ago.
- Getting AI into maintenance does not start with software. It starts with knowing what equipment is in the facility, where it is, what spare parts are on hand, and how those parts relate to specific assets. Without that foundation, even capable AI systems have nothing reliable to work with — and the floor walk to build it has to come before anything else.
Enjoying the show? Please leave us a review here. Even one sentence helps. It’s feedback from Manufacturing All-Stars like you that keeps us going!
Tweetable Quotes
- “A lot of customers do have the data. The biggest challenge is it’s super unstructured and in different systems, so getting it into a format AI can actually use is still a huge challenge.”
- “People expect predictive maintenance to surface issues, but if an asset is running well, nothing’s going to happen. No insights are sometimes good insights. That means things are operating the way they should.”
- “Historically, about 60% of a technician’s time is admin work. If you can give even 10–20% of that time back, that’s a huge gain in actual wrench time.”
Please Scroll Down for Recommended Resources from this Episode
Do you want to connect with other leaders that are moving the needle in manufacturing everyday? Then make sure to join us in the Manufacturing Happy Hour Industry Community on LinkedIn.
What We Discuss with Colin
- Whether today’s manufacturers have the data infrastructure AI actually needs, and why having data and having usable data are two very different things
- The gap between what AI-driven predictive maintenance promises and what tends to happen when facilities try to put it into practice
- Why a predictive system that shows no faults can mean things are working exactly as they should, and how confirmation bias leads teams to misread that signal
- The foundations most facilities skip when digitizing, and why jumping ahead without them creates problems that are hard to undo
- What parts information every facility should have on record, why it matters more than most teams realize, and what happens when a critical component is not catalogued
- How maintenance’s status has changed over eight years, from a cost center most facilities avoided spending on, to a core part of a facility’s digital strategy
- What AI looks like across maintenance operations today and where it genuinely adds value versus where human judgment still needs to lead
Recommended Resources
- MaintainX, helping industrial teams manage work orders, asset performance, parts, and labor with AI-driven insights that reduce downtime and boost operational excellence
- Nick Haase on Manufacturing Happy Hour, episode 206 featuring MaintainX’s Co-Founder and the company’s first appearance on the podcast
- Left Field Brewery, established in Toronto in 2013 and brews a series of baseball-inspired, distinct and full-flavoured beers
Recent Comments