Secure AI Agent · Facilities
AI applied to
the building and the assets
A specialist configured to triage work orders by severity, track preventive maintenance, keep the asset inventory current, and control service contracts and the fleet.
Companies that trust UPX
Capabilities
What the Facilities Agent
can do
Main areas of work for the Administration and Facilities AI Agent in your operation.
Severity triage
Classifies the work order and escalates anything involving risk.
Preventive maintenance
Tracks the plan and warns about the visit coming due.
Asset inventory
Keeps asset, location, and owner on record.
Service contracts
Monitors terms, contracted scope, and price adjustments.
Fleet control
Tracks licensing, servicing, and fines per vehicle.
Service quoting
Runs the quote process and organizes proposals for decision.
Skills
Capabilities that compose the specialist
Skills add specific capabilities to the Secure AI Agent according to the processes it needs to execute.
- Work-order classification
- Orders by severity and escalates immediate risk.
- Maintenance calendar
- Monitors the preventive plan and flags late visits.
- Inventory check
- Cross-checks recorded assets against what was found.
How it worksFrom an open work order
From an open work order
to a building under control
Connect your sources, define what the agent can do, and let the facility routine run within your procedures.
- Connect the administrative sources
- The agent works with the controls that already exist.Connect the asset spreadsheets, the service contracts, the maintenance plan, and the work-order inbox so the Secure AI Agent has access only to what it needs.
- Ask for the work
- Talk to the agent in natural language.Ask for work-order triage, the maintenance coming due, or a service quote through the available channels. The agent understands the context, applies the configured skills, and follows the company's procedures.
- The agent organizes. You authorize.
- From quote to authorization, with control.The agent triages, quotes, and tracks within the defined permissions. Authorizing services, approving budgets, and signing contracts stay with whoever holds administrative authority.
01
02
03
Integrations
Connected to the administrative controls
The Facilities Agent can query your controls and run tasks in the systems your team already uses.
Asana
Flow
What goes in,
what the agent does, and what comes out
From a loose work order to a building and assets on track, following your company's procedures and permissions.
Inputs
- Asset spreadsheetXLSX
- Maintenance planPDF
- Service contractPDF
Processing
Secure AI Agent
Processing the task
- Read
- Classify
- Checkrunning
- Log
Severity appliedProcedure verified
Output
Completed
Routine prepared
- Work orders triaged by severity
- Maintenance coming due flagged
- Inventory checked and updated
Control
You define how far the Agent can act
Different actions can operate with different autonomy levels, always within your company's procedures.
- 1
Query
Reads controls and contracts and answers with the reference.
- 2
Prepare
Triages work orders, quotes services, and updates the inventory.
- 3
Request review
Waits for authorization before engaging a vendor.
- 4
Execute
Performs the action within the defined limits.
Levels are configured per type of action. Authorizing services, approving budgets, signing contracts, and issuing technical reports always stay with whoever holds authority and certification. Work orders involving risk to people escalate immediately to an owner.
Get started
Put a Secure AI Agent to work.
Start on the platform or choose the plan that fits the pace of your operation.
Security and compliance
Security that can be verified.
Certifications and attestations
UPX maintains SOC 2 Type II and ISO 27001, with independent audit over its information security controls.
Privacy and regulation
- LGPD
- Operations follow Brazil's Law 13.709/2018. In AI Agent contracts, UPX acts as data processor; the legal basis remains with your company.
- Zero Data Retention
- A product policy, not a certification: with compatible providers and configurations, processed content is not retained after execution.
- Retention and deletion
- The retention policy is defined by contract. Once the contract ends, data is deleted within the agreed period.
Frequently asked questions
Common questions about the Facilities Agent
What administration and facilities teams usually ask before putting an agent into the building routine.
What if the work order involves accident risk?
That case leaves the queue. A work order showing risk to people — gas leaks, electric shock, structural issues, fire — escalates immediately to the defined owner, without waiting for triage or prioritization.Does it authorize the service and approve the budget?
No. The agent runs the quote process, lays the proposals side by side, and flags what falls outside the contracted scope. Authorizing and approving are acts of whoever holds administrative authority.Does it issue reports or certify inspections?
No. Technical reports, engineering filings, and regulated inspections belong to certified professionals. The agent tracks the validity of those documents and warns before they expire.How does it keep the inventory current?
It cross-checks recorded assets against what was reported in the count, flags location and ownership discrepancies, and keeps the movement history of every asset.Does it handle fleet fines and licensing?
It tracks deadlines, organizes the paperwork, and warns before expiry. Naming a driver, filing an appeal, and paying are actions under approval, because they carry legal and financial effect.Is our data used to train models?
No. Content processed by Secure AI Agents is not used to train UPX models or third-party models.Can we audit what the agent did?
Yes. Every action is logged: what was queried, what was proposed, when, in which system, and under which permission. The history stays available for review and auditing.
Secure AI Agent
Bring a Secure AI Agent to your administration team
Talk to our specialists and see how to adapt this AI Agent to your processes, systems, and needs.