Service
Consistent incident diagnosis on every shift, with people approving every action beyond agreed limits
We build an AI agent into your incident process, working on your runbooks, telemetry and device state. It gathers the context an engineer would, analyses it and proposes the most likely cause with its evidence. Actions come in agreed scopes, and a person approves every step outside them.
Measured impact
- ~200devices in the lab network our agent diagnoses, through 5 MCP servers and ~30 tools
- ~5 hahead, our lab agent forecast that a route leak would fill router tables
- 2,383 → 256leaked prefixes after the agent’s verified fix, as its dry run predicted
- 5%of a router’s table: the envelope inside which the agent acts alone; above it, a person approves
What changes for your organization
- Today
Engineers buried in alerts
When something breaks, syslog and alerts multiply faster than the on-call engineer can read them.
With assisted diagnosisOne incident, one picture
Repeated events are grouped and condensed into one alert with its severity, likely causes and next steps.
- Today
Diagnosis that depends on the shift
How fast a fault is found depends on who is on call and how well they know that part of the network.
With assisted diagnosisThe same investigation every time
Every incident is investigated the same way, on your runbooks and past tickets, whoever is on shift.
- Today
An investigation across many tools
Topology, device CLI, logs and alerts each live in their own tool, and the engineer stitches them together by hand.
With assisted diagnosisEvidence gathered for you
The agent pulls config, state, logs, alerts and topology together, so engineers start from the evidence.
- Today
Senior engineers on every escalation
Hard faults go to the same few experts, and their time sets the pace of every incident.
With assisted diagnosisFaster time to cause
Ranked hypotheses with their evidence reach the first responder, and experts step in where judgement is needed.
- Today
Automation too risky to switch on
An agent that changes production unchecked is a risk the organization will rightly refuse.
With assisted diagnosisAutonomy on your terms
Every proposed change is verified before it applies, and a person approves each action outside the limits you set.
What we deliver
How it runs
Every engagement starts with assisted diagnostics on your own incidents; each wider scope is agreed once the first proves itself.
Discovery
Your incident process, runbooks, telemetry and past tickets, the incident types to start with, and a plan with the scopes and limits.
Data access
Syslog, metrics, alerts, topology and device state connected to the agent through MCP tools, with role-based access and an audit trail.
Diagnosis on past incidents
The agent replays incidents you have already solved, and its causes are checked against what your engineers found.
On-call rollout
Assisted diagnostics in your live incident process, beginning with the incident types your team sees most.
Wider scope
Guided remediation or bounded autonomy, when agreed, with the Verify Gate and the limits set per class of action.
Handover
Your team runs and extends the agent, its tools and its runbooks, documented and owned in-house, with our support as long as you want it.
Three scopes, each agreed separately
Assisted diagnostics is the standard engagement. Each next scope is agreed on its own, once the one before has earned trust.
Assisted diagnostics
The agent gathers context, analyses the data and proposes the cause. The standard engagement.
Guided remediation
The agent proposes actions, and a person approves each one before it applies.
Bounded autonomy
The agent carries out approved classes of action alone, within set limits. Everything beyond them goes to a person.
Proof
Our work here comes from R&D prototypes on live lab networks and from production telemetry pipelines.
- From a failure alert to ranked root causes in minutesTwo internal proofs of concept: syslog condensed and clustered before an LLM reads it, an agent that fetches live config, state and past tickets, and ranked causes with next steps.
- A multi-MCP NOC copilot on a ~200-device networkOur agent diagnosing injected faults across a ~200-device Containerlab network through 5 MCP servers, used hands-on by ~50 engineers at AutoCon4.
- A network agent with bounded autonomy, verified before every changeA lab prototype shown at ONUG: a route leak forecast, a ranked fix, a Verify Gate before every change, and autonomy levels that send larger changes to a person.
- From telemetry to action when an SLO breaks, for FluxNinja’s ApertureFor FluxNinja, the OpenTelemetry pipelines and request classifiers that let policies turn live traffic into load shedding, autoscaling or rate limiting.
