The Platform

One causal entity graph. Four AI engines. Built for enterprise engineering teams who need answers, not dashboards.

⬡ Platform overview → ◯ Four engines → ▶ How it works → → Start free trial →

What we solve

Applicare enables teams to observe, automate, and resolve incidents faster across every stack.

★ Customer stories → → Try it free → ◯ Platform overview →
Learn
Blog
Engineering insights & deep dives
Webinars
Live sessions & on-demand recordings
Case Studies
Proven results across industries
White Papers
Research, architecture guides & reports
Customer Stories
Real teams, real outcomes
Product News
What’s new in Applicare
Adopt & Grow
Applicare University
Free courses for Applicare engineers
Learning Center
Every video lesson, searchable in one place
Documentation
Guides, APIs & integration docs
About Arcturus
Our mission, story & team
Partners
SI, MSP & technology partners
Community
Slack, GitHub & developer forum
Support
Helpdesk & customer portal
Downloads
Ops Vault
Datasheets, runbooks & toolkits
Featured Case Studies
AeroMexico
Digital ticketing · MTTR 4.5h → 11min
Leading Private Bank
MTTR 3.2h → 18min · first month
Mediclinic
Audit prep 11 weeks → 18 days
NTT DATA
80% on-call page reduction
Danube Group
94% SLO compliance
ONP
0 violations at last audit
Seygen
78% downtime reduction · GxP compliance
Insurance Tech Platform
67% P1 reduction · $2.4M saved
IIS & Server Availability
100% SLA report accuracy
Health Check Offering
4.2x ROI · 48hr delivery
Bank of Muscat
99.95% core banking uptime
Aster Hospitals
Deeper IIS application visibility
By Industry
Financial Services
Airlines & Transport
Healthcare
Government
Retail & E-Commerce
Home
ArcIn AI
Login Book a Demo
White Paper · AIOps & Root Cause

Causal AI vs.
Correlation.

Why root cause matters more than anomaly detection — and what actually changes when a platform reasons about cause and effect instead of statistical coincidence.

<60s
ArcIn root cause identificationProduct capability
<12s
Entity graph topology rebuildProduct capability
40
Services traversed to find one answerProduct capability

1. Two Different Questions

"What's unusual?" and "what's wrong?" sound like the same question asked two ways. They aren't. Anomaly detection answers the first — it tells you a metric moved outside its normal range. Root cause analysis answers the second — it tells you why, and what to do about it. Most observability tooling built over the last decade is very good at the first question and structurally unable to answer the second, because it was never given the information it would need to: the causal relationships between the things it's watching.

This paper is about that gap, and about the specific architectural choice — a causal entity graph instead of a metrics-correlation engine — that Applicare's ArcIn uses to close it.

2. What Correlation-Based Tools Actually Tell You

A conventional anomaly-detection or correlation engine watches time series and flags statistical deviations: a metric crossed a threshold, or moved in a way that's uncommon relative to its history. When several such deviations happen close together, the tool may group them because they're temporally correlated — they happened around the same time.

That is useful information, but it is not causal information. Two metrics moving together does not establish that one caused the other, or that either caused the underlying problem — both could easily be downstream symptoms of a third thing the tool never measured directly. The result, familiar to anyone who has been paged at 2am, is a wall of simultaneous alerts and no way to tell which one is upstream of the others.

3. The Causal Entity Graph: A Different Starting Point

Applicare's platform is built around a continuously updated causal entity graph — a live model of every service, host, container, database, and dependency in an environment, and the causal relationships between them, rebuilt in under 12 seconds as the environment changes. This is the foundation every other capability in the platform sits on top of, including ArcIn.

The difference in one sentence: a correlation engine asks "what else moved around the same time?" A causal entity graph already knows which services depend on which, so it can ask "which of the things that moved is actually upstream of the others?"

4. Traversal, Not Pattern-Matching: How ArcIn Gets to an Answer

When an engineer asks ArcIn a question like "why is checkout slow?", ArcIn does not search for statistically similar historical incidents. It traverses the causal entity graph from the symptom backward through real dependency edges — this service calls that service, that service reads from that database, that database's replica just fell behind — until it reaches an event that plausibly explains what changed: a deploy, a configuration change, a traffic surge, a resource constraint.

That traversal is what makes a plain-English answer possible in under 60 seconds. ArcIn isn't summarizing a dashboard full of correlated alerts for a human to interpret — it's walking the same causal chain a senior engineer would walk by hand, across as many as 40 services in a single incident, and reporting the node where the chain actually starts.

What that traversal looks like

⚠ checkout-svc — p99 latency spike (symptom)
↑ calls
orders-db connection pool — 96% utilization
↑ caused by
OrderRepository — N+1 query pattern introduced
↑ introduced by
Deploy 14:32 UTC — commit touching order_items eager-load logic (root cause)

5. A Worked Comparison

The same incident, reasoned about two different ways:

StepCorrelation-based approachCausal entity graph (ArcIn)
SignalLatency, error rate, and DB metrics all flag around the same timeSame signals, but already attached to graph nodes with known relationships
GroupingGrouped because they're temporally closeGrouped because they're causally connected — one is genuinely upstream
OutputA list of correlated alerts, ranked by statistical strengthA single causal chain, ending at the event that explains it
Human task remainingInterpret which alert is the cause, usually by process of eliminationConfirm the fix; the cause is already named

6. Where Correlation Still Earns Its Place

None of this makes correlation and anomaly detection obsolete — it makes them a different layer of the same system. Applicare's IntelliSense engine uses per-entity behavioral baselines and anomaly detection specifically because that is the right tool for the job it does: noticing that something has changed before there's enough information to explain why, including zero-day patterns that have no historical precedent to pattern-match against.

The point is not "anomaly detection is wrong." It's that anomaly detection answers "something is different" and a causal entity graph is what turns that observation into "here is what's different, and why" — and conflating the two, treating correlation output as if it were root cause, is where a lot of AIOps tooling overpromises.

7. What This Changes for the On-Call Engineer

In a correlation-driven workflow, the engineer's first ten minutes are spent doing causal reasoning that the tooling didn't do: opening each alerting dashboard, checking deploy timelines by hand, asking around in Slack about who touched what. In a causal-graph-driven workflow, that reasoning already happened before the engineer opened anything — the plain-English answer is waiting, with the specific service, the specific commit, and a recommended fix attached.

The practical effect isn't just speed, though under-60-second root cause is a meaningful speed difference on its own. It's that the engineer's attention goes to deciding whether the recommended fix is right, not to reconstructing what happened in the first place.

8. Adopting a Causal Model Without Ripping Out What Works

Teams don't need to discard existing monitoring to get the benefit of a causal entity graph — Applicare ingests OpenTelemetry and existing metric sources into the graph rather than requiring a wholesale replacement. The entity graph and ArcIn typically run alongside existing anomaly detection during evaluation, so the difference between "something moved" and "here's why" is visible on the same incidents, side by side, before any tooling gets retired.

See ArcIn reason about a real incident
Watch the causal traversal happen live, on your own environment.
Request a Demo →