AI Agent Operations

When a new incident fires,
it usually rhymes with one you have seen before

Incident Similarity Engine matches a fresh incident against your incident archive. It surfaces the top 3 past incidents with similar signals and shows what fixed them. The on-call engineer (or the responding agent) sees "this looks like inc-4502 from last quarter, these three steps resolved it." Most incidents have ancestors; the engine finds them.

Get Started Talk to Sales
app.novaaiops.com / incident-similarity-engine
● LIVE
Top 3
past matches
Symptom
+ service signature
Auto
runbook suggestion
Confidence
shown per match
How Matching Works

Symptom signature plus service signature

Each incident gets a signature: the symptom signature (which SLIs breached, which signals fired, in what order) and the service signature (which services were involved, how the service-graph cluster looked). Matching compares the live incident's signature against archived ones using both signatures jointly. Top 3 matches over a confidence threshold are surfaced.

  • Symptom signature: breached SLIs, fired signals, sequence, captures the incident shape
  • Service signature: involved services and graph cluster, captures where it hit
  • Joint match: both signatures must align to count as similar; one alone is not enough
app.novaaiops.com / incident-similarity-engine · match
Resolution Suggestion

What worked last time, ranked

For each match, the engine extracts the resolution path (what tools, in what order, with what outcome). The top match's resolution is offered as a starting suggestion. The on-call engineer sees the suggestion and the data behind it; choosing it is one click; ignoring it is also one click. The system never forces a path.

  • Extracted resolution: tools called, order, outcome, pulled from the matching past incident's ledger
  • Top suggestion offered: on-call sees the top match's resolution as a starting point; not an order
  • Ignoring is fine: engineer can ignore the suggestion; the system records the choice for future learning
app.novaaiops.com / incident-similarity-engine · suggest
Coverage Report

How often the engine matches

Not every incident has a clear past match. The page reports match coverage (percent of incidents with a confident match) and trend. Match coverage typically grows over time as the archive grows. New tenants start with low coverage; mature tenants see 70%+ match rates within a year.

  • Match coverage trend: percent of incidents with a confident match, tracked weekly
  • Early-tenant low: first 3 months are below 30% match; archive needs to grow before coverage takes off
  • Mature 70%+: mature tenants see > 70% match rates; the engine is reading their history back to them
app.novaaiops.com / incident-similarity-engine · coverage
Privacy

Matching never crosses tenants

Similarity matching is strictly per-tenant. Your incident archive is your archive; another tenant's incidents never appear in your match results. Aggregate model improvements that benefit everyone are derived only from anonymized signature shapes, never raw incident data.

  • Tenant-scoped archive: your archive is private; matches only come from your own history
  • No cross-tenant leak: cross-tenant lookups are blocked by Context Redactor and Egress Scanner
  • Aggregate model, anonymized: platform-level model improvements come from de-identified signature shapes only
app.novaaiops.com / incident-similarity-engine · privacy
Video walkthrough coming soon

Subscribe to Nova AI Ops on YouTube for demos, tutorials, and feature deep-dives.

Your incident history is your best playbook

Generic runbooks miss what makes your environment yours. Similarity Engine pulls fixes from your own track record.

Get Started Request a Demo