Secure AI Agent · ISP
AI applied to
running your provider
A specialist configured to keep regulatory deadlines on the calendar, answer abuse against the clock, flag routing hygiene issues, and signal the subscriber about to churn.
Companies that trust UPX
Capabilities
What the ISP Agent
can do
Main areas of work for the Internet Service Provider AI Agent in your operation.
Regulatory calendar
Tracks filing deadlines and organizes the inputs.
Abuse handling
Triages the report, finds the subscriber, and drafts the reply.
Routing hygiene
Flags prefixes without IRR, dirty routes, and missing filters.
Subscriber retention
Signals who keeps complaining and is about to leave.
Link quality
Cross-checks tickets against metrics and flags the bad segment.
Legal requests
Organizes the received request and the response deadline.
Skills
Capabilities that compose the specialist
Skills add specific capabilities to the Secure AI Agent according to the processes it needs to execute.
- Abuse triage
- Correlates IP and timestamp with the responsible subscriber.
- Prefix checks
- Compares the announcement against the registry and flags drift.
- Obligation calendar
- Monitors regulatory deadlines and warns in advance.
How it worksFrom the received report
From the received report
to a network under control
Connect your sources, define what the agent can do, and run the operation with deadlines and evidence in hand.
- Connect the provider's sources
- The agent works with what the operation already produces.Connect the monitoring, the subscriber base, the abuse inbox, and the routing registries 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 abuse triage, the month's regulatory deadlines, or a prefix check through the available channels. The agent understands the context, applies the configured skills, and cites the evidence.
- The agent prepares. Operations decide.
- From preparation to execution, with control.The agent triages, correlates, and drafts within the defined permissions. Submitting filings, changing routing, and suspending subscribers stay with the responsible team.
01
02
03
Integrations
Connected to the systems the network feeds
The ISP Agent can query your metrics and run tasks in the systems your team already uses.
Grafana Prometheus 
Flow
What goes in,
what the agent does, and what comes out
From a raw log to an operation meeting its deadlines, following the provider's procedures and permissions.
Inputs
- Abuse reportEML
- Subscriber baseCSV
- Routing tableLOG
Processing
Secure AI Agent
Processing the task
- Read
- Correlate
- Checkrunning
- Draft
Evidence citedProcedure verified
Output
Completed
Operation prepared
- Abuse correlated to the subscriber
- Unregistered prefix flagged
- Regulatory deadline on the calendar
Control
You define how far the Agent can act
Different actions can operate with different autonomy levels, always within the provider's procedures.
- 1
Query
Reads metrics and registries and answers with the evidence.
- 2
Prepare
Correlates the abuse and drafts the reply.
- 3
Request review
Waits for approval before acting on the network.
- 4
Execute
Performs the action within the defined limits.
Levels are configured per type of action. Submitting regulatory filings, changing production routing, suspending subscribers, and answering legal requests always stay with the responsible team and, where applicable, with legal.
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 ISP Agent
What providers usually ask before putting an agent into the operation.
Does it submit filings to the regulator?
No. The agent keeps the calendar, organizes the inputs, and flags what is missing before the deadline. Submission and responsibility for the filing stay with the operator, who answers for the content.Does it touch our routing?
Not without approval. Filters, prefixes, and routes take customers down if they go out wrong, so they are sensitive actions by design: the agent flags the drift between what is announced and what is registered, and the change follows the engineering process.How does abuse handling work?
It reads the report, correlates IP and timestamp with the responsible subscriber, and drafts the reply within the procedure's deadline. Suspending or blocking the subscriber is a human decision, with the history already assembled to support it.Does it answer court orders?
No. It organizes the request, gathers the requested data, and sets the deadline, but responses to legal requests go through legal. The agent exists so nothing expires forgotten in an inbox.Does it help retain subscribers?
It signals who complains repeatedly, cross-checks the ticket against the link's metrics, and shows the pattern. The retention offer and the negotiation stay with the commercial team.Is subscriber 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 provider
Talk to our specialists and see how to adapt this AI Agent to your processes, systems, and needs.