Probable diagnosis
With AI Autopilot (Multiple AI Agents) on corrective work orders, marIA reads the ticket. It suggests the asset, the symptoms, the probable causes and a recommended action. Whoever reviews it skips the reading, not the judgment.
Choose which cookies you accept. You can change this at any time from “Cookie settings” in the footer of every page. Cookie policy
They make the website work, remember this choice, keep your conversation with the assistant if you use it, and protect the forms from bots. They cannot be turned off.
During your visit we remember the campaign source you arrived with and the page you landed on, so we know which campaigns and pages bring us requests. Cloudflare Web Analytics counts visits without cookies and does not depend on this option.
Used to measure our campaigns on Google Ads, LinkedIn and Meta. None is active on the website today.
AI-CMMS · marIA in attendo CMMS
When you get in, the overnight breakdown already has a probable diagnosis and a criticality score. The technician’s voice note is written up on the work order. And you make the call.
Cold room 2 compressor won’t start
Automation and AI
With AI Autopilot (Multiple AI Agents) on corrective work orders, marIA reads the ticket. It suggests the asset, the symptoms, the probable causes and a recommended action. Whoever reviews it skips the reading, not the judgment.
Every corrective work order gets a score from 0 to 100. It weighs asset criticality, impact, SLA risk, status and recurrence. You adjust the weights.
The technician records what they found and what they recommend. marIA transcribes it and leaves a summary on the work order and in the asset history, without anyone typing it up.
You ask which line has the most downtime or how MTBF is doing. The chat answers in plain language, read-only, with the 22 KPIs on the dashboard and the same figures.
From the work order, the technician asks for a torque value and marIA answers, citing the manual and the page. The answer comes from your documentation, not someone else’s.
“If an asset has two corrective work orders in 30 days, notify the maintenance manager.” You describe it and marIA proposes the flow. You review it, switch it on and, if it does not work for you, undo it.
How it works
This is how it is used day to day, on the same document as the rest of the modules.
Your key, your provider and a monthly budget that stops the AI once it is reached.
It is turned on per document type. For preventive maintenance, the usual choice is to leave it without AI.
By QR code, email or portal. marIA suggests the probable diagnosis and the score, and explains it in the AI activity.
They review, assign and schedule. If they claim the work order, the agents stop touching it.
marIA suggests the probable diagnosis, scores criticality, transcribes and summarizes voice notes and answers questions about your data. For predictive maintenance, AI models work on readings from your sensors and IoT devices, connected natively. It does not assign, repair or close work orders. Every operation is logged with who started it, the model and its cost. Spending has the monthly cap you set. See attendo CMMS.
Honesty
It does not assign technicians, repair anything or close work orders.
Works with
It suggests and assigns. A person decides.
Micro-agents that score and prioritize. You take the wheel.
See AI Autopilot (Multiple AI Agents)SELECT supplier, COUNT(*) … GROUP BY supplier Ask in plain language. Get answers from your data, with the source.
See AI-Chat and DB AssistantFlows, phased processes with approvals, and AI inside the flow
See Flows and AI-FlowsChecklist · Safety inspection
Inspections with photo, signature and location, closed on site
See attendo ChecklistGlossary
Maintenance
Equipment criticality
Asset criticality is the impact that an asset’s failure has on service, production or safety. It helps you share out a maintenance budget that is always limited.
Maintenance
Corrective maintenance is the work done after a piece of equipment fails, to bring it back into service.
Maintenance
PdM
Predictive maintenance decides when to intervene based on the real condition of the equipment, measured through vibration, temperature, power draw or oil analysis, not by calendar.
Frequently asked questions
Yes. Predictive maintenance uses AI models on readings from your sensors and IoT devices, which connect natively. And marIA helps you prioritize today’s breakdown.
Yes, which is why it is a probable diagnosis and labeled as such. A person reads it before acting.
For the diagnosis, the text of that work order is sent. The rows in your tables, such as assets and failures, only go to Scaleway or to your Microsoft 365 Copilot. The KPI chat sends an aggregated summary, with the names of plants, assets, plans and clients, to the provider you configure for it: if you do not want those names to go to another provider, configure Scaleway or your Microsoft 365 Copilot.
Yes, in full. AI-CMMS is an optional layer of attendo CMMS and is turned on piece by piece.
No. They send a voice note and it shows up in writing on the work order. It is less work, not more.
Request a demo
We will show it to you with your own document types and the way you work. If it is not a fit, we will tell you.
Would you rather talk first?