NetPulse agents
8 agents that detect, group, name a root cause and file the incident. Rules and statistics rather than a language model, so every call is reproducible.
Agentic AI for SD-WAN operations
NetPulse watches the telemetry and decides what matters. CEEZ Crew investigates, explains and rehearses the fix. Nothing changes until you approve it, at the level you set.
Already have access? Sign in to NetPulse →
Latency climbs from 20 to 65 ms over about three hours
Detection Agent · availability never flipsDegraded for its hour of the week, with nothing over a fixed line
Anomaly Agent · learns what normal looks like for that hourThe link, its tunnel and two applications become one situation
Correlation Agent · symptoms inhibitedSuspected root: the provider’s middle mile, not the branch edge
Root-Cause Engine · applications are never the rootThe Transport specialist confirms it. Closed in 2.9 minutes
CEEZ Crew · every claim cites its querySteer voice and video to the Internet path until MPLS recovers
Remediation Agent · approval first, rollback attachedLatency and voice quality are back inside their limits, verified against the alarm that fired
Verification Agent · the carrier fixes MPLS, then traffic fails backExample: a silent brownout at a Berlin branch, from first signal to verified recovery.
14 kinds of source become one set of facts and one entity graph.
From signal to sign-off
Each stage has an owner and each hand-off is on the record. The first three follow fixed rules. The Crew reasons. A person approves.
Fourteen kinds of source become one picture of your network.
Breaches are scored against each entity’s own baseline, and repeats are folded.
Related alerts become one situation, and a root cause is named, or handed to a person when it is unclear.
Specialists query the data, a commander adjudicates, and every claim cites its query.
A gated fix with a rollback plan, checked against the alarm that fired.
The last 24 hours.
Each stage removes what another stage already explains: repeats, then flaps, then symptoms of a root.
How a root cause is chosen, on an example Berlin brownout.
Two applications, their tunnel and one link are all outside their own baselines.
The tunnel’s breach is traced to the link underneath it. Applications are evidence, never the root.
A provider is only a candidate when three or more links degrade across two or more sites. Here one link did.
The MPLS link explains the tunnel and both applications below it, and nothing above it is breaching. It is the root cause.
Results vary with your network, data sources and traffic patterns.
The agents
32 agents in four groups. Each one lists what it reads, what it produces and how much it may do on its own.
8 agents that detect, group, name a root cause and file the incident. Rules and statistics rather than a language model, so every call is reproducible.
17 workers take an incident from triage to a verified close. Specialists query the data and a commander adjudicates.
3 workers on a schedule rather than an incident: baselines, forecasts and maintenance windows.
4 workers that turn telemetry into SLA claims, vendor scorecards, config audits and executive briefs.
Use cases
Pick the situation. Each use case is a short procedure: how to recognize it, which agents are already on it, what you do, and what the answer means.
A circuit, a region or a device has stopped. You need the cause and the next move.
Everything reports healthy and users are still unhappy.
The queue is deeper than anyone can read.
An alert that could be an attack, or could be a rule gone wrong.
Credits you are owed and spend you should not be making.
Warnings before the breach, and the failures no threshold will catch.
Decide what happens next, and build the screens your team watches.
Measured outcomes
Fewer pages, correct root causes and earlier warning, each with how it was measured.
96%
fewer pages than raw alerts
24-hour test window
277 raw alerts became 11 pages through de-duplication, correlation and suppression of symptoms.
How it was measured →77%
of calls correct
29 benchmark incidents
17 of 22 calls. Where the evidence is unclear it says so and hands over to a person.
How it was measured →57 min
median warning
28 benchmark incidents, gradual failures
2 of the 5 gradual-onset failures were flagged before they breached.
How it was measured →Worked examples
Berlin · brownoutChicago · hard-downBerlin · securityControl
Agents start by suggesting. A fix moves up a level only on evidence, and moves back down on a regression. The level is set per playbook and per kind of incident.
The agent proposes and explains. People do the work.
Recommend onlyA named person approves each step before it runs.
Approval firstRoutine work inside the limits runs on its own, and tells you.
Automatic with notice, once earnedRuns inside a bounded policy envelope, on the record, reverting on a regression.
Within a set envelopeCEEZ Crew
A worker has a role, instructions, constraints, a model and an autonomy tier. Tools are granted step by step and every run leaves a record. NetPulse hands incidents to whichever team you point it at.
Crew specialistQuestions
NetPulse is the set of agents that watch telemetry, group alerts, name a root cause, file incidents and gate fixes. They use rules and statistics, so every call is reproducible. CEEZ Crew is a workforce of model-backed workers that NetPulse hands an incident to: specialists that query the data, a commander that adjudicates, and writers that explain.
Only what you approve. Every fix is a proposal with its blast radius, its rollback and the way recovery will be verified. You approve it, hold it, or take the recommendation into your own change process.
From a 24-hour window and a set of reference incidents with known causes. The outcomes page shows each figure with what it counts and what to keep in mind. Your own results are on the Accuracy screen once it is running on your network.
The incident goes to a person with the evidence gathered so far, rather than a guess. The decision is logged, so you can see how often it happens and why.
Not for detection, correlation, noise handling, forecasting or root-cause analysis. The Crew workers use a model connection you provide. Automatic investigations are off by default and are capped per day and by spend.
SNMP and traps, gNMI, gRPC dial-out telemetry, NETCONF, OpenTelemetry, NetFlow and IPFIX, syslog, Kafka and message buses, REST polling, Prometheus, TWAMP and path probes, cloud flow logs and metrics, inventory and CMDB, and log shippers.
Open Situations and pick the use case that matches what you see.