Schedule of values validation that puts every location on the map, checks its COPE data and its value, and leaves the decision to the underwriter
Every location geocoded and its COPE gaps flagged before the property is priced.
See one case, screen by screen ↓Checking every location on a broker’s schedule of values before the account is priced: that the address places on the right building, that the COPE data — construction, occupancy, protection, exposure — agrees with property records, permits and surveys, and that the building value is in line with what it costs to rebuild. Schedule of Values Validation does those checks with six agents and leaves each decision to the underwriter.
How to choose AI solutions for insurance →
Updated
A commercial property renewal arrives as the broker’s schedule of values: a spreadsheet in the broker’s own layout, three tabs, thirty-odd columns, the year built buried in the notes. Construction, occupancy, sprinkler and year built fields are blank or wrong, addresses are partial, and building values have been rolled forward for years while the cost to rebuild kept rising.
Before anyone can price it, an underwriting assistant re-keys it into the carrier’s layout, the cat modelling analyst geocodes it and finds locations dropped on a ZIP centroid, and the underwriter chases the broker for the gaps in several separate emails. The under-valued buildings are the quiet risk: under a coinsurance clause, a building carrying half the limit the clause requires is paid about half of a partial loss. Today those are often found at the claim, not at the quote.
Estimated split, in working hours, for one 42-location schedule — about 2.5 days by hand (our estimate), about an hour with the solution (the target).
Six agents read, place, check and value every location on the schedule; the underwriter decides.
Harlow & Vane sends the Tidewater Crest Logistics renewal: 42 warehouses, cold stores and truck terminals from Victoria, Texas to Pensacola, Florida, TIV $989.49M, effective 1 November. Here is what happens next, screen by screen, in the working solution.
Elena opens Accounts: seven schedules, each a stripe of its locations coloured clean, fixed by an agent, needs you or agents reading. Tidewater Crest Logistics — 42 locations, $989.5M TIV, quote due Fri 23 Oct — is marked Ready for you.
The schedule reader maps the broker’s 31 columns across three tabs to the 24 standard fields. The geocoder drops every pin on the map, then the property data checker and the valuation checker work through each location while the pins change colour.
“Valuation checker · value per sq ft against rebuild cost for construction, occupancy and area · 5 under 80% · 1 over 130%”
Green is clean, amber the agents fixed, red needs her. Of 42 locations, 22 are clean, 12 were fixed by an agent and 8 need Elena. Beside the map, the COPE table shows each location’s construction, occupancy, protection and exposure, with suspect values outlined, value per square foot and a bar against rebuild cost. TIV moves from $989.49M submitted to $1,001.71M checked.
On the map, without anyone looking for it: “Baytown · insured at 48% of rebuild”.
2215 Calcasieu Channel Rd is not in the address file, so it matched only the 70601 ZIP centroid, in flood Zone X. The geocoder searched the parcels on the channel road and found a 96,000 sq ft cold store 5.6 km west, on the ship channel, in Zone AE. It shows the old pin hollow, with a dotted line to its best match — and does not move it on its own.
“Agents’ best match · cold store, 96,000 sq ft · drag pin 23 here”
Elena moves pin 23 onto the cold store. It re-geocodes to the roof, the hazard mapper re-runs, and the row, the flood zone and the exposure file update together. Needs you drops to 7.
“Pin 23 moved to the roof · 5.6 km west · flood Zone X → Zone AE, BFE 8 ft · exposure file updated”
One switch recolours every pin by insured value against rebuild cost: under 60%, 60–80%, 80–130% and over 130%. The comparison uses the checked area and occupancy, so a wrong square footage or a missed freezer cannot hide an under-valued building.
4410 Port Road is a 212,000 sq ft tilt-up distribution warehouse, masonry non-combustible, built 1998, ESFR sprinklered. The schedule carries $9.8M — $46 per sq ft. Rebuilding it in the Houston area costs about $96 per sq ft, $20.35M. The value has been $9.8M on every schedule since 2019 while the area cost index rose 45%.
The location page shows the rebuild build-up (212,000 sq ft × $96 × 1.00 for the Baytown area), the building value on each schedule beside the cost index, every field with its source, and the agents’ run on this location. Elena decides: accept the checked value or keep the broker’s.
“With 90% coinsurance the building limit of $9.80M is 54% of what is required: a $4.0M partial loss would be paid at about $2.14M, before the deductible.”
One email to Megan Cole at Harlow & Vane, copied to Raj Patel: the Pasadena sprinklers the 2025 survey found in the office only, the Beaumont freezer addition, the Gentilly row counted twice, five building values under 80% of rebuild. The 12 small corrections the agents made are listed, not asked. Beside it: what the answers change — +$29.99M of building value on the five under-valued locations, −$17.77M for the duplicate, $34.71M into flood Zone AE.
“Untick a question to leave it out. Nothing goes until you send it.”
The exposure file shows total insured value by flood zone and by distance to the coast, submitted beside checked, how precisely each location is placed, and the fields the model reads. Floor elevation is known for 6 of 41 locations, so the other 35 go as unknown and the model uses its neutral assumption — never a favourable value.
“Unknowns stay unknown — never coded as a credit.”
The same renewal, seen by the five people who carry it — what their week looked like, and what it looks like now.
Six agents read, place, check and value every location on the schedule; the underwriter decides.
Reads any broker spreadsheet layout and maps its columns to the 24 standard fields, using last year’s confirmed mapping for that broker first; normalises construction and occupancy codes.
Standardises each address and places it on the roof, then the parcel; flags ZIP-centroid and intersection matches, suggests the right building and finds two rows on one parcel.
Compares each row’s COPE fields, area, year built and roof with property data, building permits, risk engineering surveys and last year’s schedule.
Compares value per square foot with the cost to rebuild that construction and occupancy in that area, and finds values rolled forward unchanged.
Adds flood zone and base flood elevation, distance to the coast, wind tier and protection class to each placed location.
Drafts one email of questions for the broker, each with its evidence, and leaves out what the agents already fixed.
Decides every finding. The agents propose; a named person decides.
Ask about any location, value or question on the schedule — or tell it what to change. Every answer cites its source.
Why is Baytown insured at 48% of rebuild?
Because its value has not moved since 2019. 4410 Port Road is a 212,000 sq ft tilt-up distribution warehouse. Rebuilding it in the Houston area costs about $96 per sq ft, $20.35M; the schedule carries $9.8M, $46 per sq ft — the same figure on all eight schedules since 2019, while the area cost index rose 45%. With 90% coinsurance, a partial loss would be paid at only about half.
Which locations would move in the flood model?
Two. Location 23, Lake Charles, was on the 70601 ZIP centroid in Zone X; the building is on the ship channel, Zone AE with a base flood elevation of 8 ft — $34.71M of value. Location 28 is location 27 counted twice, so $17.77M in Zone AE comes out.
Draft the questions for Harlow & Vane
Ready: 10 questions in one email to Megan Cole — five building values under 80% of rebuild, the Pasadena sprinklers, the Beaumont area, the Pensacola freezer, the Mobile construction and the Gentilly duplicate. The 12 small fixes are not asked. Nothing is sent until you press send.
Refer any location under 60% of rebuild to Daniel Okoye
Done. New rule: “Any location below 60% of rebuild is referred to Daniel Okoye.” On this account it catches location 17 (48%); across your open accounts, 3 more. It applies from today and is logged as version 7 of the settings.
13 screens from the working solution, on its sample data. Pick one to see it large.
Thresholds, cost tables and who signs are settings — versioned and logged — not a project.
| Setting | Default | Choose from |
|---|---|---|
| Flag as under-insured below | 80% of rebuild | Any share, in 5% steps |
| Flag as possibly over-insured above | 130% of rebuild | Any share, in 10% steps |
| Rebuild cost tables | Kestrel Point cost tables, Oct 2026 | Your cost tables · a valuation service |
| Flag a value not moved for | 3 schedules or more | 2 · 3 · 5 schedules or more |
| Placement needed before pricing | Roof or parcel | Roof only · Roof or parcel · Street or better |
| Blank fields that stop pricing | Construction, occupancy, year built, sprinkler, area | On · Off |
| Questions go to the broker | Only when the underwriter sends them | On · Off |
| Co-signature above | $750M TIV | $500M · $750M · $1B TIV |
Every figure is labelled: a target the solution is built to, an estimate, a typical published result, or a proven one.
“demo” = seen in the working solution, on its sample account data · “target” = the design goal, measured in the live solution · “estimated” = our estimate · “typical” = published figures (Ping Data, the cost of manual SOV processing — 2–4 hours for a small complex SOV; RebuildCostASSESSMENT.com via Insurance Business, 2025 — UK properties insured at 66% of rebuild cost on average). People, companies, brokers and buildings named on this page are fictional — characters and sample data in the working solution.
Checking every location on a broker’s schedule of values before the account is priced: that the address places on the right building, that the COPE data — construction, occupancy, protection, exposure — agrees with property records, permits and surveys, and that the building value is in line with what it costs to rebuild. Schedule of Values Validation does those checks with six agents and leaves each decision to the underwriter.
Yes. The schedule reader reads any spreadsheet layout and any number of tabs, and maps the broker’s columns to the 24 standard fields, using last year’s confirmed mapping for that broker first. In the demo it maps 31 columns across three tabs. A blank stays blank and is flagged; it is never filled with a guess.
The valuation checker compares each building’s value per square foot with the cost to rebuild that construction and occupancy in that area, using your rebuild cost tables. It flags values under 80% of rebuild, over 130%, and values rolled forward unchanged for three schedules or more — all thresholds you set. It works on the checked area and occupancy, so a wrong square footage cannot hide an under-valued building.
The geocoder places each address on the roof, then the parcel. ZIP-centroid and intersection matches are flagged, with the building it believes is right, and go to the underwriter, who moves the pin onto the building. The flood zone, distance to the coast and protection class update with it.
No. The agents propose; the underwriter accepts the checked value or keeps the broker’s for every finding. No agent overwrites the broker’s value, changes a limit or sends anything to the broker, and every step is on the activity trail.
A model-ready exposure file with the checked locations, how precisely each is placed, and any pins still to fix named at the top. Unknown fields such as floor elevation are sent as unknown, never coded as a favourable value.
Yes. The under-insured and over-insured flags, the rebuild cost tables, how long a value may stay unmoved, the placement needed before pricing, the fields that stop pricing when blank and the TIV above which a co-signature is needed are all settings. Every change is versioned and logged.
The Agentic Solution Engine builds and deploys it from your requirements and documents — your schedule layout, rebuild cost tables, underwriting guidelines and a sample of past schedules — and it goes live once every quality gate has passed. We will walk you through it on your own schedules first.
Submissions ready to price the same day, poor fits declined in minutes.
1-min demoLoss Run Analysis AutomationLoss summaries in minutes, not an hour per account, each claim traced.
1-min demoUnderwriting Authority & Referral ManagementAnswers in seconds, each referral tied to its rule and authority letter.
1-min demoWe’ll run Schedule of Values Validation on a few of your own past schedules of values.