Skip to content

Underwriting in hours, with the reasoning attached

Commercial submissions waited 3.5 days for a first look and inbound leads waited 3 hours for routing. An intake and scoring system now produces a cited risk memo for every submission, approved by a human underwriter.

Illustrative example. Names and results are fictional and do not represent verified customer outcomes.

Published

Measured result

Underwriting cycle time
3.5 days → 11 hours Underwriting cycle time 6-month window
Speed-to-lead, inbound
3h → 4min Speed-to-lead, inbound median, all inbound enquiries
Qualified meetings booked
+34% Qualified meetings booked 8-person team, one quarter
Book a call

The situation

Kestrel Financial underwrote commercial policies from broker submissions arriving as email with attachments — loss runs, financials, applications, occasionally a photograph of a form. Median time from submission to first underwriter look was 3.5 days, and 19% of submissions were declined for reasons visible on page one.

Separately, their eight-person commercial team routed inbound web enquiries by hand. Median speed-to-lead: 3 hours, worse on Fridays and non-existent at weekends. Brokers who didn’t hear back in a day went elsewhere.

Two problems, one root cause: the first pass on any inbound item was a human doing mechanical work with no queue discipline.

What we found in the teardown

We spent a day with their two most senior underwriters writing down how they actually decide: the factors they look for, the order, the disqualifiers, the weights, the point at which they stop reading. It took four hours and produced a two-page rubric neither had ever seen written down.

That rubric became the specification and the eval. We replayed 400 historical submissions through it manually before building anything, and measured agreement with the recorded decision. The rubric alone agreed 86% of the time — which told us the constraint was reading speed and consistency, not judgement.

What we built

Six weeks, in their VPC with their own model endpoints, in two parts.

Intake and memo. Submissions are parsed, classified and checked for completeness; missing documents trigger an automatic broker request. For complete submissions the system produces a structured memo: factors found, source document and line for each, rubric version applied, a confidence figure, and an explicit list of what it could not verify. Low confidence routes to a senior underwriter by design, not by exception. No policy is bound without a human approving the memo.

Inbound routing. Enquiries are enriched, scored against the same rubric, matched to territory and assigned in minutes, with a drafted first response the rep edits rather than writes.

The compounding part is the override loop. Every underwriter override is captured with a reason code, aggregated weekly, and turned into either a rubric change or a new eval case.

Result

Over six months:

  • Underwriting cycle time 3.5 days → 11 hours
  • Speed-to-lead 3h → 4min
  • Qualified meetings booked +34% for the eight-person team in one quarter
  • First-pass agreement with senior reviewers 86% → 94% after two quarters of override feedback
  • Page-one declines now surfaced in under 20 minutes

The artifact their regulator liked most wasn’t the model. It was a documented, versioned rubric and a queryable record of every decision and every override.

“Everything ran in our VPC with our keys. Security cleared it in nine days, which has never happened here before.”

— Marcus Bell, Chief Information Security Officer, Kestrel Financial

Same workflow, same volume, measured either side.

The left figure is what the workflow cost before we arrived, out of their own reporting. The right is what it cost after, over the window named beneath it.

Underwriting cycle time
3.5 days 11 hours 6-month window
Speed-to-lead, inbound
3h 4min median, all inbound enquiries
Qualified meetings booked
+34% 8-person team, one quarter

Other workflows we took apart.

Same method, different queue. Each one states its baseline, its window and its denominator.

Meridian Health
Meridian Health

Support answers that stop costing twelve minutes each

A 240-seat support org was answering policy questions from a 900-page handbook and four wikis. One cited answer layer, wired into the ticket, cut average handle time by 38% in seven weeks.

Read the case study
Average handle time
−38% Average handle time across 1.2M annual contacts
First-contact resolution
+22% First-contact resolution 90 days post-launch
Teardown to production
7 weeks Teardown to production three engineers
Northwind Logistics
Northwind Logistics

Invoices that match themselves, exceptions that route themselves

40,000 invoices a quarter hit a matching rule set that failed on every non-standard PO line. Chaining extraction, matching, exception routing and ERP write-back moved auto-match from 78% to 94%.

Read the case study
Invoice auto-match rate
78% → 94% Invoice auto-match rate on 40k invoices/quarter
Month-end audit prep
5 days → 4 hours Month-end audit prep first two quarters
Cost per processed document
−81% Cost per processed document vs. prior BPO rate
Book a call

Request a thirty-minute session.

Tell us about your workflow. We’ll reply to arrange a time; submitting this form does not book a calendar slot.

We'll only use this to schedule your session. See our privacy policy.