The kind of team this fits: a Lloyd's market marine syndicate, roughly 140 vessel submissions a month, 8 underwriters, hull, machinery and P&I lines.
The morning before
140 vessel submissions a month, eight underwriters, and a five day wait for a quote means two brokers can bring the identical risk and reasonably expect two different answers, depending on whose desk it landed on that week.
How this could run
Not a feature list. The actual sequence, from the moment the case lands to the moment someone signs it.
- 01
Vessel, voyage and route data get assessed together
Hull, machinery, cargo and P&I risk are evaluated from one submission, not stitched together across specialists.
- 02
A different model checks the first opinion
A SPAR adversarial pass flags where coverage terms or pricing would have been inconsistent with a similar risk.
- 03
The underwriter still binds it
Sign-off stays with a named underwriter on every risk that's bound.
Image, inside Zen StudioScreenshot of a Zen Studio canvas configured for a workflow like this one.
What doesn't change
A named underwriter still binds every risk. The adversarial check flags the inconsistency, it doesn't sign the slip.
What this could mean
Illustrative, based on the shape of a workflow like this one. The real number depends on the case, the team, and how it's configured.
5 days → 6 hoursSubmission to quote turnaround
85%+Underwriting output consistency
Image, inside Zen PilotScreenshot of the Zen Pilot dashboard or explainability panel for a run of this workflow.
Where this lives in the platform
For an active underwriter, a workflow like this starts as a conversation with Zara, describing the process in plain language and getting a first draft of the team back in the same session. Zen Studio is where engineering opens that draft, sets the guardrails node by node, and versions it before it goes live. Zen Pilot is where it actually runs, and where anyone can watch a case move through it in real time, node by node, with the reasoning attached.
