Since we launched Wording Analyzer, our clients have been using it to compress what used to be hours of manual contract review into minutes: handling complex slip packs, cross-document comparisons, and clause-level checks at scale. Today, we're releasing V3, and the scope has changed.
This isn't an incremental update. V3 extends Wording Analyzer from the contract into the portfolio, and from the review into the submission. The result is a platform that covers the full lifecycle of a piece of business, from the moment a slip pack arrives to the point where it's a structured, decision-ready dossier sitting inside your book.
Here's what this release brings to your teams.
Portfolio analytics, at any point in time
The question underwriters and wordings teams have always struggled to answer at portfolio level is deceptively simple: what does my book actually say? Which clauses are trending? Where are the concentrations? How is wording quality distributed across lines?
V3 delivers a live answer. Portfolio analytics now surfaces emerging clause trends across your entire assumed book, tracks exposure concentrations by clause type or territory, and gives you a quality distribution view, not at renewal time or as a static report, but at any point in the cycle. Whether you're running a mid-year audit, preparing for a Lloyd's review, or trying to understand the silent exposure implications of a new market clause, the data is there.
Submission-level intelligence: slip pack to dossier
One of the most time-consuming tasks in reinsurance operations is extracting the material facts from a submission. Insured, perils, limits, deductibles, sub-limits, conditions, scattered across a slip, a wording, an I&L, sometimes multiple endorsements. V3 structures that extraction automatically.
Upload a slip pack and Wording Analyzer produces a structured dossier: every material detail extracted, classified, and ready to inform the underwriting decision. Less time spent assembling information, more time spent on the judgement that actually requires expertise.
Clause variance analysis
For teams managing large books, consistency at the clause level is one of the hardest things to monitor. The same clause type — a cyber exclusion, a sanctions condition, a terrorism carve-out — appears in slightly different forms across hundreds of contracts. Individually, none of the variants look alarming. Collectively, the drift adds up.
V3 introduces clause variance analysis: a single view of one clause type across your entire book, surfacing outliers, identifying drift between cycles, and flagging the precedents that matter. It's the kind of analysis that used to require a dedicated legal project; now it runs on demand.
A cross-line clause library, managed at scale
Standard clause management has historically been a per-LoB problem. Teams maintain separate libraries, standards drift, and the link between the library and the actual review workflow is manual at best.
In V3, the clause library operates at tenant level: a single source of truth across all lines of business, with role-based access, full versioning, and direct integration into the review workflow. When your standards evolve, every active review reflects the change. When an underwriter flags a non-standard clause, it feeds back into the library. The loop closes.
Deeper control logic: acceptability and favourability scoring
Not all clause deviations carry the same weight. A broader definition of "occurrence" shifts risk in a different direction than a narrowed pollution exclusion. V3 introduces acceptability and favourability scoring that quantifies the direction and magnitude of each clause's impact, identifying clearly whether a given wording shifts risk toward the insured, the cedant, or the carrier.
This gives wordings teams and underwriters a shared, objective basis for negotiation, escalation, and governance. The scoring is built into the review workflow and exportable as part of the decision record.
Agentic capabilities: ask your wording anything
The final piece of V3 is one that changes the day-to-day experience for every user on the platform, not just the specialists. Any underwriter can now interrogate a wording in plain English, search across documents, ask a specific question, summarise a section, and get a sourced answer in seconds.
This isn't a generic chatbot layered on top of a document. The agentic capabilities in V3 are built on the same insurance-native models that power the rest of the platform. Answers are grounded in the actual documents, sourced to the relevant clause or paragraph, and auditable. The aim is to make wording expertise accessible to everyone on the team, not just those who've spent years reading contracts.
What stays the same
Everything that made Wording Analyzer work in the first place is still there: multi-document joint reading across slip, wording, I&L, and endorsements; automated playbook-driven review by LoB; contract match with semantic redlining; and the security and governance architecture that our clients rely on: tenant-isolated, EU-hosted, with full audit trail and SSO.
Find out more
If you'd like to see it in context of your own book, get in touch with our team. Contact us.
| Domaine d'Application | Bénéfices Clés grâce aux Graphes de Connaissances |
| Prévention | Identifier les causes racines communes à plusieurs sinistres pour proposer des actions préventives. Détecter les causes secondaires pour limiter la propagation des dommages. |
| Tarification | Proposer des segmentations plus fines des assurés en fonction des chaînes de causes réelles. Mieux évaluer l'impact d'une exclusion de garantie (par exemple, "Exclusion de l’usure de machines"). |
| Provisionnement | Comprendre les dynamiques d'évolution des pertes et identifier les causes qui, étonnamment, ne mènent à aucun coût, pour affiner les réserves financières. |