The new Digel

Every industrial software tool you use today is a questions app. Your CMMS, your ERP, your BI dashboards, your SCADA UI, all of it. They all work the same way. You have to know what to ask. You open the tool, you dig through menus, you remember to check the asset that's been bothering you, you run a report, and if you asked the right question you get the right answer. If not, you find out later, usually when something breaks.

That model is exhausting. The operator with the most context is also the operator with the least time, and the burden of curiosity lands squarely on them.

We think this is the actual problem. Not the UI, not the data model, not the integration story. The direction.

From questions to answers

The new Digel is an answers app. Instead of waiting to be asked the right question, it tells you what you need to know. The things you didn't think to check. The things nobody put on your dashboard. The things the agent noticed because it's been reading every signal, every document, and every conversation across your plant all day.

This is the reframe the rest of the product is now organized around. Digel is an AI-native maintenance and quality management system, designed for a world where the software works out what matters and the human decides what to do about it.

Nobody had anything nice to say

The "maintenance and quality management" half is new, and we want to explain where it came from, because we didn't set out to build a CMMS.

In every pilot we ran this past year, we asked teams about the tools they rely on day to day. When we got to the maintenance management system, we heard the same thing on every site. Not "it's OK." Not "fine once you learn it." Actively negative. Zero positive words. This is a product category people are paying real money for and actively avoiding.

At the same time, we kept bumping into an awkward fact: the CMMS contains some of the most valuable data in the plant. Machine status, failure history, spare parts, process information, who fixed what and when. An industrial AI that can't see this data is working with one eye closed.

So we baked it in. The CMMS lives inside Digel now, on top of the same context graph as everything else. It's easy enough that operators actually use it, and it's open to the rest of the product, which means the agents can reason across maintenance history the same way they reason across sensor data or documentation.

Triage is where humans and agents cooperate

Triage is the center of the new Digel. It's a short, prioritized list of things Digel thinks deserve your attention right now, each one written in plain language with the reasoning attached and one click to act on it.

The important word is cooperate. Triage isn't the agent writing to you from behind a wall. It's a shared surface. The agent proposes, you decide. You can accept an item, reassign it, dismiss it, or argue with it. If you disagree, you push back in chat and the agent re-investigates against live data. Items you close become history, items you dismiss teach the agent what you care about, comments the team leaves get pulled back into the context graph.

A Triage item looks something like this:

Pump 4 vibration is drifting. RMS has been climbing for 36 hours and is now 18% above its normal band. The same pattern preceded the bearing failure on Pump 2 last October. There's an open work order on Pump 4 from three weeks ago that was never closed out. Want to open a maintenance issue?

No separate approval queue, no forms, no training. The human in the loop is just the decision you were going to make anyway.

@digel, anywhere

The chat agent isn't a separate place you go when you're stuck. It's woven into every surface of the product. You can @digel in any comment, on any issue, in any note, and it will answer using the full context of the thing you're looking at and everything it connects to. Ask it what the history on this asset looks like, what the recommended next step is, or why the last repair didn't hold. The answer comes back in the same thread, with links back to the data it used.

You can also create new issues straight from chat. Type "new issue on Line 3, motor 3 making a grinding noise, noticed this morning" and Digel files the issue, links it to the asset, attaches the last few weeks of sensor history, and drops it into your team's queue. No form, no manual tagging, no switching tools.

How it actually works

Every conversation, sensor stream, work log, document, downtime record, and operator note flows into the same context graph. The agents work continuously inside that graph, watching for the things that matter. When they find something, it shows up in Triage, or as a direct answer where you already are. What comes out the other side isn't just issues. It's suggestions, improvements, automations, and answers to the questions you didn't have to remember to ask.

The arrows go both ways on purpose. Context isn't built once and frozen. Every item you close, every comment you leave, every disagreement you have with the agent goes back into the graph and makes the next answer better. The more your team uses Digel, the more Digel understands what your plant actually looks like, and the better the answers it brings back.

Why this matters

When the software waits to be asked, the best operators carry the whole plant in their heads. That works until they leave, retire, or have a bad day. When the software brings things to you, the institutional knowledge moves out of the heads and into the system, where everyone on every shift gets the same heads-up. The new person on the team is immediately as effective as the one who has been there for fifteen years, because they share the same colleague.

That's the bet under the new Digel. Not a better filing cabinet. Not a prettier CMMS. A colleague that's actually paying attention, and tells you what you need to know before you know to ask.

Where we are

The new Digel is in production with real customers, not a roadmap slide. The CMMS is live, Triage is live, the chat agent is live everywhere in the product, and the context graph underneath it is real. Operators are creating issues, asking @digel questions, and arguing with triage items on their phones in the hallway between shifts.

If you're running an operation and you're tired of being the one who has to remember to ask, we'd like to talk to you. We learn something from every one of these conversations. Send us a note at hello@digel.io.