Problem 01
Submissions you should have written first
Acquisitions, expansions and leadership changes drive premium decisions weeks before the broker call. Most carriers find out when the submission lands — already shopped.
Insurance
Price the risk you can see. Detect the fraud you cannot.
For underwriting, claims, fraud and distribution leaders across P&C and specialty.
Underwriting depends on data you don’t control. Claims depend on stories you can’t verify. Compass fuses internal policies with external evidence and adversarial networks, so underwriters price on reality and claims investigators find rings, not incidents.
The problem
Loss ratios drift because the risk was mispriced at bind. Claims fraud is chased case by case while organised rings recycle addresses, phones, repair shops and clinicians across dozens of policies. Distribution can’t see which broker book actually generates profitable business.
Data we integrate
- 01Policy admin, underwriting workbench, claims systems (Guidewire, Duck Creek, Sapiens)
- 02Third-party risk data — property, weather, telematics, IoT, health, credit
- 03Claims documents (FNOL forms, medical reports, invoices, PDFs) — parsed into structured facts
- 04Company registries, sanctions, adverse media, court records
- 05External adversarial signals — repair-shop rings, phone/address recycling, staged-loss patterns
- 06Distribution & broker data — production, cancellation, complaint patterns
How we contextualize
- Entity resolution across policyholders, claimants, providers and third parties — one identity per actor.
- Network view: shared phones, addresses, IBANs, repair shops and clinicians across policies and claims.
- Fraud scoring that explains itself: every score comes with the ring, the evidence and the precedent case.
- Underwriting enrichment at quote time — external signals injected into the risk model in seconds.
- Distribution health view: which broker cohort generates loss-heavy business vs. profitable growth.
What's broken today
The structural problems we solve.
Problem 02
Renewals defended too late
Broker movement, claims experience and competitive scoping converge into a renewal lost long before the renewal meeting happens.
Problem 03
Specialty cross-sell left on the table
Cyber, D&O, environmental and parametric lines fit obvious triggers — but matching them to the right account at the right moment is structurally manual today.
AI Skills for this industry
Risk & Compliance
Insurance Fraud Detection
Detects coordinated claims networks, staged incidents and repeat actors across policies, providers and geographies.
Run skill
Trade & Supply Chain
Counterparty Network Map
Reveals hidden ownership chains, intermediaries and shared directors across a portfolio of counterparties.
Run skill
Risk & Compliance
Third-Party Due Diligence
Builds an evidence-backed dossier on any counterparty — ownership, litigation, sanctions, adverse media — in minutes instead of days.
Run skill
Investigation
Adverse Media Sweep
Runs multilingual adverse media checks across news, court filings and gazettes — deduplicated, ranked and cited.
Run skill
Investigation
Case File Builder
Assembles a court-ready case file from fragmented evidence — timelines, actors, sources, chain of custody — with every claim cited.
Run skill
What you get out
Reports, decks, Excel, dashboards and alerts — ready to ship.
Brief (PDF)
Underwriting risk brief
Per-quote PDF with external signals, network exposure and precedent losses — cited to source.
Graph
Claim network graph
Interactive graph of a suspicious claim — connected claimants, addresses, IBANs, providers.
Excel
Ring exposure model
Structured Excel: rings detected, member policies, total gross exposure, recommended action per policy.
Dashboard
Fraud ops dashboard
Live queue of claims by ring risk, SLA, aging and analyst load.
Alert
New-ring alerts
‘New ring detected: 14 policies, 3 addresses, 1 clinician — €480k exposure. Investigate.’
Audit log
Decision audit log
Every underwriting or claims override captured with reason, evidence and reviewer.
A concrete case
One suspicious motor claim → 22 connected policies and €680k of avoided payouts.
A single motor claim looked routine. Compass resolved the claimant, the repair shop and the tow-truck IBAN across the whole book, exposed a ring of 22 policies with overlapping addresses and shared providers, and produced a court-ready case file. Payouts on the affected claims were held, brokers involved were flagged, and the underwriting model was updated the same week.
Order of magnitude
What insurance teams see in the first two quarters.
+28%
Submission-to-bind rate on new business
First-mover advantage on M&A and expansion triggers.
+15%
Renewal retention on top-200 accounts
Earlier visibility on broker, claims and competitive scoping signals.
3×
Specialty cross-sell briefs per quarter
Trigger-matched openings routed to the right underwriter.
< 24h
From M&A trigger to outreach
Recommended action with draft language, ready for the producer.
How Compass operates
Your weekly insurance operating rhythm.
- 01
New business radar
M&A, expansion, leadership change across covered segments — each routed to a producer with the right line of business pre-matched.
- 02
Renewal defense queue
Top accounts entering 90-day window, ranked by broker movement, claims signal and competitive activity.
- 03
Specialty triggers
Cyber incidents, regulatory exposure, sustainability disclosures matched to the specialty line and underwriter best placed to write.
- 04
Portfolio committee brief
One view of the book's movement — submissions, renewals, specialty pipeline — with explainable evidence for every recommendation.
Outcomes
What changes when you operate with Compass.
- Higher hit rates on commercial new business
- Better renewal retention through proactive engagement
- Faster identification of cross-sell openings
- Sharper underwriting through continuous context
- Better coordination across producer, underwriter and specialty
- Defensible decisions with full evidence trail
Common questions
What insurance leaders ask us first.
- Is this for carriers, brokers or both?
- Both. Carriers use Compass to prioritize underwriting capacity; brokers use it to surface new-business and renewal triggers across their book.
- Does it work for excess and specialty lines?
- Yes — the play library is built around trigger events that disproportionately affect specialty lines like cyber, D&O, environmental and parametric.
- How is it different from a data enrichment vendor?
- Enrichment hands you data; Compass hands you a ranked, explainable action — the right account, the right line, the right owner, with the brief already drafted.
Trust by design
Evidence, explainability, audit — built into every output.
Source-level evidence
Every signal, score and recommendation links back to the underlying record — the email, the filing, the transaction, the document — with the source visible at a click.
Explainable recommendations
No black-box outputs. Each priority states why it was promoted, which signals contributed, which were declassed, and which model version produced it.
Audit trail by default
Signals, model versions, reviewers and actions are logged and reconstructable later — ready for internal control, regulators and your own governance.
Human-in-the-loop
Compass recommends. Authorized people decide. Every consequential action requires a named reviewer who can confirm, override or annotate the reasoning.
See Compass on your sector.
30 minutes. Your accounts, your pipeline, your signals. We'll show you the actions Compass would recommend today.