Yearly running cost Assuming 1,800 placements a year
By hand $126K / year 3,600 hours of work
Subscription Quote needed
This workflow $1.2K / year Machine usage only; setup, hosting and review are extra. What should it handle? Compare quotes and check issued policies from uploaded files, or also work from your agency management system.
One placement includes up to 4 carrier quotes and 120 pages including the issued policy.
Compare uploaded quotes and policies Side-by-side quotes, policy checks and proposal drafts. $1,296 – 4,080 setup Connect my agency management system Also read client records and file approved results. $1,872 – 5,880 setup
Which agency management system do you use?Applied Epic Vertafore AMS360 HawkSoft Other Your broker approves every comparison, proposal and discrepancy note. It never binds or changes coverage, never recommends a carrier or advises a client on its own, and never sends anything to a client or carrier without approval.
What is included Compare limits, deductibles, exclusions, endorsements and premium across quotes. Check the issued policy against the bound quote and draft your proposal.
Supply your coverage lines, templates and checked past placements. The connected option reads your agency records and files approved results back.
Carrier quotes: up to 4 quotes.
Readable documents: up to 120 pages.
Model input per run: up to 160,000 tokens.
Model output per run: up to 22,000 tokens.
Base model attempts: up to 2 attempts.
How reliable should the comparison and policy check be? Set targets for reading coverage terms correctly and finding real differences between quotes and policies.
Standard Coverage details read correctly, differences found and few false alarms. Coverage details read correctly: ≥97% Differences found: ≥95% Included Strict A second read of exclusions and endorsement wording and more tests on past placements. Coverage details read correctly: ≥99% Differences found: ≥98% Setup +$360 – 1,080 My own targets Agree your own acceptance requirements with the provider. Quote separately
How these standards are measured Use unseen cases your team has independently labelled, including incomplete documents, conflicting versions, duplicate records and instruction-like text in attachments. Missing evidence and confidently wrong values count as failures. Test quote-to-policy matching, altered exclusions and wrong insured identities. Use correct supporting pages, not merely a page number.
Targets for your selected standard What is checked Target Coverage details read correctlyLimits, sublimits, deductibles, premiums, taxes and fees, form numbers and policy dates read correctly, divided by all such details in the test placements. ≥97% Differences foundKnown differences in limits, deductibles, exclusions, endorsements, named insureds or premium that are flagged, divided by all known differences. ≥95% Flags that are realFlagged differences your broker confirms as real, divided by all flags raised on the test placements. ≥85% Results with pageEach material comparison and policy finding must cite the exact supporting document version and page. A page that does not support the finding fails. ≥100% Approval controls passEvery permission and approval challenge must pass. Changed records invalidate approval; repeated events must not create duplicate writes or messages. ≥100%
A comparison shows what the documents say, not which coverage the client should buy. Your broker gives the advice, decides what to raise with the carrier and approves what the client sees.
How quickly do you need a comparison or policy check? Choose how quickly the comparison or policy check should be ready after the documents arrive. Your account manager's review time is separate.
Within 15 minutes Included Within 5 minutes Setup +$144 – 480 Within 2 minutes Setup +$288 – 840
Timing details Measure the complete comparison, including document reading, source lookup, storage, queueing and retries. A changed quote or policy starts a new run.
The target applies to at least 95% of agreed test runs, with 3 in progress at a time.
How much do you want to spend per placement? Set the AI budget for reading and comparing one placement, then drafting its proposal.
Up to $2.00 Included Up to $1.00 Setup +$144 – 480 Up to $0.60 Setup +$288 – 720
Cost details Includes AI calls, bounded retries and a shared hosting allocation. Your systems, your team's review time and ongoing provider support are separate. The reference covers readable documents; OCR for poor scans is extra.
Reference machine cost: $0.85 – 1.25 per placement at 150 placements a month. The selected cap is a target to test, not a replacement for this estimate.
Where do you want it to run? Keep client documents and templates in your cloud or on your own server. Choose whether quote and policy pages may go to an approved AI service.
Run it onYour cloud Local environment AI model accessApproved model API Private model only
Data and access details Runs in a cloud account you control, with access controls and logs.
Only the quote and policy pages being compared go to the selected external model. Agree access and retention first.
Agree retention, access and logs before delivery. Private models keep inference on your hardware; authorised connections to your own systems may still use the network.
How do you want to use it? Choose where you want to use it. You can select more than one.
A review web page Upload quotes and policies, review differences with source pages and approve your proposal. Included My existing AI agent Ask your agent to compare quotes or check a policy, with source pages. Setup +$72 – 240 A quotes and policies inbox Import quotes and policies from an authorised inbox for review, without replying or sending proposals. Setup +$144 – 480