Three tiers — Pay-as-you-go from $200, Heavy User from $800, Enterprise custom. Every action — pipeline run, single agent, chat message — costs a known number of credits. No monthly minimum. No seats. Credits never expire.
Vortic is invite-only during early access. Approved users top up via Stripe.
Pay-as-you-go
$200minimum top-up · $0.10 per credit
For teams running their first AI-assisted underwriting workflows. Approximately 110 full pipeline runs per top-up. Credits never expire.
A full pipeline run uses 18 credits ≈ $1.80. Your $5 free covers ~3 full runs.
Agent
What it does
Credits
Cost
Parse
PDF / submission text extraction
1
$0.10
Triage
Fast appetite scoring + routing
1
$0.10
Risk Analyst
Construction, occupancy, loss history
2
$0.20
Flood & Cat
EA / FEMA / wildfire exposure
2
$0.20
Pricing
Rate adequacy vs market benchmarks
2
$0.20
Compliance
Appetite, FCA / NAIC checks
2
$0.20
Treaty
Accumulation + reinsurance
2
$0.20
Portfolio
Book fit + concentration
2
$0.20
Memo Synthesis
Decision memo from all outputs
5
$0.50
Command Chat
Per message — answer or task creation
1
$0.10
Full pipeline
Parse + 6 specialists + memo
18
$1.80
What is a “system of action”?
A system of record stores what happened. A system of intelligence predicts what could happen. A system of actionis where the underwriter sees the day's required decisions, makes them in one click — bind / decline / refer with downstream notifications wired — delegates to specialist agents and reviews their output, and coordinates with brokers and teammates without leaving the surface.
Command Center IS the system of action. Every widget either surfaces a decision, executes one, or moves it forward. That's why credits are per-action and not per-seat: you only pay for actual work.
How Vortic compares
Vendor
Pricing
Positioning
Federato
$50K+/yr
Risk Operations Center
HX
Custom
Spreadsheet replacement
Artificial Labs
Custom
No-code workflows
Vortic
$0.10/credit
System of action — pay only for what you run
Frequently asked questions
What does Vortic actually do for an underwriter?
Takes a broker submission — PDF, email, spreadsheet — and in under 30 seconds returns a fully-cited memo: insured details extracted and reconciled, postcode pulled to flood zone, loss history surfaced, TIV sanity-checked across line items, pricing benchmarked against your book, treaty utilisation projected, compliance red-flags raised. The underwriter reads the memo and clicks bind, decline, refer, or query. The judgment stays with the human — the lookups go to the system.
What underwriting lines does Vortic support?
Today: commercial property and casualty in the UK and US, including E&S coastal, retail commercial, and Lloyd's coverholder books. Specialty lines (cargo, professional indemnity, construction, cyber) are supported with custom agent prompts during onboarding. We do not currently target retail personal lines.
How long does onboarding take?
Two weeks from contract to first live submission for a typical MGA. Week one: connect your data sources (broker email inbox, existing book of bound risks, treaty programme). Week two: tune the risk agent against your appetite, adjust the memo template, set role permissions, train the team on Command Center. Self-serve sign-up runs the same product on demo data; design-partner onboarding is the white-glove version.
How does Vortic handle data we cannot send to third-party LLMs?
Three layers. First, every submission goes through PII redaction before any model sees it — insured names, broker emails, postcodes are masked in the audit log by default. Second, you choose what data joins the prompt: ground-truth lookups (flood, postcode geolocation, FEMA NFIP) are configurable per-agent. Third, Enterprise customers can route the platform to their own private LLM deployment, so no inference traffic leaves your VPC.
How do you ensure the AI does not make up flood zones, loss history, or pricing?
Ground-truth blocks. For any factual claim — flood zone, postcode, sanctions, regulatory thresholds — Vortic injects verified data from the source (EA Flood, FEMA NFIP, postcodes.io, your loss-history database) directly into the prompt and instructs the model to cite or refuse. The memo carries explicit citations back to the source. If the lookup fails, the memo says "no data" instead of guessing.
What audit trail does the platform keep for compliance?
Every model call is logged with the prompt version, model used, tokens consumed, latency, and structured output. Every memo cites its sources. Every decision (bind / decline / refer / query) is captured immutably with the underwriter who made it, the rationale, and the agent outputs at that moment. Designed against Lloyd's coverholder oversight and PRA SS3/19 model governance from day one. The full table is exportable for regulator submission.
How does Vortic integrate with our existing systems?
Inbound: a webhook endpoint where brokers (or your own broker portal) can POST submissions directly into your queue, authenticated with a bearer key. Outbound: HMAC-signed event webhooks fire on every bind / decline / refer to your policy admin system, treaty platform, or finance ledger. CSV import is available for bringing existing bound books into Vortic for portfolio analysis.
How does the team and permissions model work?
Four roles per organisation: owner, admin, member, viewer. Owners can change billing and ownership; admins manage members and integrations; members can run pipelines and bind; viewers see decisions but cannot execute. Email-invite flow with a 14-day token. A user can belong to multiple organisations (useful if your firm carries delegated authority for several MGAs).
How do credits and pricing work?
Three tiers. Pay-as-you-go starts at $200 minimum top-up at $0.10/credit (≈ 110 full pipeline runs). Heavy User starts at $800 at $0.08/credit (≈ 555 full pipeline runs, 20% volume discount). Enterprise is custom. $5 free credit on signup to evaluate. Credits never expire. A full underwriting pipeline runs ~18 credits ≈ $1.40-$1.80 per submission depending on tier. Compare to a fully-loaded underwriter at roughly £0.30/minute over 60-90 minutes of manual triage: £22-£27 per submission.
What happens if a regulator asks why a specific risk was bound?
You open the submission history page. It shows: every agent that ran, the inputs they received, the outputs they produced, the prompt version active at that moment, and the underwriter's final decision with timestamp and rationale. The full chain reconstructs in seconds. We have built this for the moment of regulatory scrutiny, not against it.
What is a "system of action"?
A system of record stores what happened. A system of intelligence predicts what could happen. A system of action is where the underwriter sees the day's required decisions, makes them in one click, delegates to specialist agents, and coordinates with teammates without leaving the surface. Command Center is the system of action; Workbench is the deep submission canvas; Run Pipeline is the playground. One source of truth, three densities.
How does Vortic compare to ChatGPT or general AI tools?
A general AI tool can read a PDF and summarise it. Vortic runs nine specialist agents in coordinated parallel, grounds each one against verified data sources (EA, FEMA, postcodes.io, your loss-history), produces an underwriter memo with structured citations, sits behind a human bind gate, and logs every call for the regulator. Different problem, different posture.
How do I get access?
Sign up at getvortic.com to start with $5 free credit on demo data. For team deployment, design-partner pilots, or enterprise integration, the contact form routes to the founder for a 24-48 hour reply.
Ready to try Vortic?
We onboard MGAs, coverholders, brokers, carriers, and reinsurers. Tell us about your book.