Build a Predictive Maintenance Workflow with Snowflake and MaintainX

5 comments

Apps it uses

I built a predictive maintenance workflow in Awish for one of my manufacturing clients.

The client had machine telemetry, production data, and maintenance history spread across different systems. The problem wasn’t collecting the data—it was spotting failure risk early enough to act.

I built a custom Awish workflow that continuously checks machine telemetry and production signals in Snowflake alongside asset, meter, and maintenance history from MaintainX. When it detects abnormal performance or increasing failure risk, it identifies the affected equipment, estimates the likely operational impact, and prepares a recommended maintenance action.

Nothing is scheduled automatically at that point. The recommendation first goes to the maintenance manager in Microsoft Teams for approval. Once approved, Awish creates and assigns the work order in MaintainX, then keeps tracking and updating its status until the maintenance is completed.

The useful part is that the system does not wait for a machine to fail before maintenance starts, but it also does not let AI make the maintenance decision on its own. The analysis is automated, while the actual intervention still requires human approval.

Step-by-step

  1. I described the maintenance process I wanted in the Awish chat.
  2. Awish planned the workflow and selected Snowflake, MaintainX, and Microsoft Teams for the required steps.
  3. I connected the client’s accounts and approved the automation plan.
  4. Awish continuously analyzed production and telemetry data in Snowflake together with MaintainX asset, meter, and maintenance history.
  5. When it detected abnormal behavior or increasing failure risk, it identified the affected equipment and estimated the likely operational impact.
  6. It prepared a recommended maintenance action and sent it to the maintenance manager in Microsoft Teams.
  7. Once the manager approved the recommendation, Awish created and assigned the work order in MaintainX.
  8. The workflow continued tracking the work order and updating its status until the maintenance was completed.

Trigger → Analyze → Approval → Action Machine signals → Failure-risk analysis → Teams approval → MaintainX work order

5 comments

Have a question about this workflow, or a way to improve it?

Log in to comment Create a free account
Brooke Benson Pro The Rundown team

Thanks for sharing this workflow, Alper!

Prasanth Kumar

The human-in-the-loop piece you built around the Teams approval before any work order gets created is exactly the right call for manufacturing environments where a wrong maintenance decision can cascade into unplanned downtime. I've been working closely with plant teams on similar setups, embedding directly into their systems to get this kind of workflow from proof-of-concept to something operators actually trust and use daily. One thing I keep running into is that the approval step sounds clean on paper but gets messy when the maintenance manager is on the floor or mid-shift. How are you handling situations where the approval sits unanswered while the machine signal keeps trending in the wrong direction?

Nabeel Shaikh

The gap you're describing between spotting the signal and actually having time to act on it is exactly where most predictive maintenance setups fall apart, even when the data pipeline is solid. I've spent the last couple years helping U.S. manufacturers get this kind of workflow out of pilot and into something their teams can actually own and operate. Curious about the telemetry side though: are the machines surfacing clean sensor data or is a big chunk of the work happening upstream just to make the signals usable?

Ashok Kumar Gurram

The gap you're describing between spotting failure risk and having enough lead time to actually act on it is exactly where most predictive maintenance efforts stall out, even when the data is all there. I've been working on this specific problem with US manufacturers, embedding directly into their systems to get that pilot to production gap closed. One thing I'm curious about: when you handed this workflow off to your client, what did ongoing model drift or retraining look like for them operationally?

Posting guidelines