# Ptally

> Ptally is an AI enabled insurance pricing platform for insurers and MGAs that has served over 50 million quotes. Insurers build, test, launch and manage their rates and rules on the Ptally rating engine, with expert help to build models included and no implementation fee.

Blog posts are linked as Markdown. Every link also works without `.md` as a normal web page. The full text of the site's key content is at https://ptally.ai/llms-full.txt.

## Pages

- [Home](https://ptally.ai/): The platform, how it works and pricing plans.
- [Model building](https://ptally.ai/developer): A worked UK pet insurance model: inputs, every step and a real quote response.
- [Quote debugging](https://ptally.ai/developer/debugging): Each part of a quote's debug output explained, with referred and declined examples.
- [Project documents](https://ptally.ai/developer/documents): Uploading policy wordings and product guides so AI clients can answer cover questions with the clause and page.
- [MCP](https://ptally.ai/developer/mcp): Connecting ChatGPT, Claude or Cursor to https://app.ptally.ai/mcp, and the tools available.
- [API](https://ptally.ai/developer/api): REST API endpoints for projects, versions, tests and quotes.
- [Example models](https://ptally.ai/examples): Default models for common lines of business, each selectable in Ptally.
- [Blog](https://ptally.ai/blog): Articles on AI in insurance pricing, distribution and regulation, plus platform guides.

## Example models

- [Personal motor](https://ptally.ai/examples/motor): A single-vehicle private car model rated by territory, vehicle group, driver age and no claims discount.
- [Home buildings and contents](https://ptally.ai/examples/home): A single-property home model pricing buildings and contents separately by region and construction.
- [Travel](https://ptally.ai/examples/travel): A per-traveller travel model that rates each traveller by age, then applies destination and trip length.
- [Business owner's policy (BOP)](https://ptally.ai/examples/bop): A multi-location small business package rating property and liability per location.
- [Commercial property](https://ptally.ai/examples/commercial-property): A single-location fire and allied perils model using construction class, protection class and sprinklers.
- [Commercial general liability](https://ptally.ai/examples/general-liability): A class and exposure rated CGL model with increased limit factors and a claims load.
- [Workers' compensation](https://ptally.ai/examples/workers-comp): A per-class-code workers' compensation model with a state load and experience modification.
- [Commercial auto fleet](https://ptally.ai/examples/commercial-auto): A fleet model rating each vehicle, then applying state, claim-free experience and safety programme factors.
- [Management liability (D&O and cyber)](https://ptally.ai/examples/management-liability): A combined directors and officers and cyber model rated by revenue band, industry and limit.
- [Inland marine](https://ptally.ai/examples/inland-marine): A coverage-type rated inland marine model for contractors' equipment, fine art and cargo.
- [Commercial earthquake](https://ptally.ai/examples/earthquake): A standalone catastrophe model rating building value by hazard band, construction and deductible.
- [Equipment breakdown](https://ptally.ai/examples/equipment-breakdown): A boiler and machinery model rated by equipment type, occupancy, age and inspection status.
- [Enhanced annuity from a health questionnaire](https://ptally.ai/examples/enhanced-annuity): A joint life annuity priced from a scanned health form, a prescription and two pension statements, with a referral for an unmatched medicine.

## Articles

- [Project documents: AI answers about cover, straight from your policy wording](https://ptally.ai/blog/ai-answers-from-your-policy-wording.md): Upload policy wordings, product guides and IPIDs to a Ptally project. AI clients connected over MCP can then answer what a product covers, citing the clause and page, alongside the price.
- [Annuities: a better journey for advisers and customers, more premium kept and healthier A/E](https://ptally.ai/blog/annuity-providers-advisers-customers-and-ae.md): How annuity providers can price individual annuities straight from client documents, give intermediaries and their own pension customers a faster journey, keep more maturing premium and protect mortality experience by underwriting class.
- [How to turn an Excel rater into an API](https://ptally.ai/blog/excel-rater-to-api.md): A practical guide to turning an Excel rating workbook into a pricing API: what the endpoint looks like, mapping cells to inputs, reproducing rounding, testing against the workbook, versioning and response times.
- [How to price commercial fleet insurance: rating factors and a worked example](https://ptally.ai/blog/how-to-price-commercial-fleet-insurance.md): How a commercial auto fleet is rated vehicle by vehicle, then adjusted for state, claims record and risk management, with a worked quote priced by a real rating model.
- [How to price cyber insurance for SMEs: rating factors and a worked example](https://ptally.ai/blog/how-to-price-cyber-insurance.md): How SME cyber insurance is rated from revenue, industry, data held and security controls, with a worked quote for a professional services firm priced by a real rating model.
- [How to price SME package insurance: rating factors and a worked example](https://ptally.ai/blog/how-to-price-sme-package-insurance.md): How a small business package policy combines property and liability across several locations, with a worked quote for a two-site retailer priced by a real rating model.
- [How to price trucking insurance: rating factors and a worked example](https://ptally.ai/blog/how-to-price-trucking-insurance.md): The rating factors that drive trucking insurance premiums, from vehicle weight and radius to cargo and telematics, with a worked quote for an eight-truck long haul fleet priced by a real rating model.
- [Ptally vs Akur8 Deploy](https://ptally.ai/blog/ptally-vs-akur8-deploy.md): How Ptally compares with Akur8 Deploy, Akur8's cloud rating engine: where each fits, how rates get into production, testing and approvals, AI features and commercial model.
- [Ptally vs building a rating engine in house](https://ptally.ai/blog/ptally-vs-building-a-rating-engine-in-house.md): Build or buy? An honest comparison of writing your own insurance rating engine with Ptally: engineering cost, testing, audit trail, versioning, serving at aggregator volume and maintaining rate changes.
- [Ptally vs Duck Creek Rating](https://ptally.ai/blog/ptally-vs-duck-creek-rating.md): How Ptally compares with Duck Creek Rating for insurance rating: who each suits, standalone and suite use, how rates are built and changed, testing, deployment, AI and cost.
- [Ptally vs Earnix](https://ptally.ai/blog/ptally-vs-earnix.md): How Ptally compares with Earnix Price-It for insurance pricing and rating: who each suits, how models are built and changed, testing and approvals, AI features and commercial model.
- [Ptally vs Guidewire PricingCenter](https://ptally.ai/blog/ptally-vs-guidewire-pricingcenter.md): How Ptally compares with Guidewire PricingCenter for insurance pricing and rating: who each suits, how it relates to PolicyCenter, how models are built and changed, testing, AI and cost.
- [Ptally vs hyperexponential (hx Renew)](https://ptally.ai/blog/ptally-vs-hyperexponential.md): How Ptally compares with hyperexponential's hx Renew pricing platform: who each suits, Python models versus readable JSON models, testing and approvals, AI features, the Guidewire acquisition and commercial model.
- [Ptally vs Oracle Insbridge](https://ptally.ai/blog/ptally-vs-oracle-insbridge.md): How Ptally compares with Oracle Insurance Insbridge Enterprise Rating (formerly Insbridge Rating and Underwriting): architecture, how rates are built and changed, testing, deployment, AI and cost.
- [Ptally vs WTW Radar](https://ptally.ai/blog/ptally-vs-wtw-radar.md): How Ptally compares with WTW Radar and Radar Live for insurance pricing and real-time rating: who each suits, how models are built and changed, testing and approvals, AI features and commercial model.
- [Choosing a rating engine for a new MGA](https://ptally.ai/blog/rating-engine-for-a-new-mga.md): A decision guide for new MGAs choosing a rating engine: what capacity providers expect, speed to market, broker and aggregator distribution, audit trail and the cost model that suits a book with no premium yet.
- [Rating engine with no implementation fee: how it works](https://ptally.ai/blog/rating-engine-with-no-implementation-fee.md): How a rating engine with no implementation fee works: who pays for the build, what is included, how the provider earns its fee, and the honest trade-offs compared with a licence and a separate implementation project.
- [Ptally compared: established pricing platforms and new AI entrants](https://ptally.ai/blog/ptally-vs-insurance-pricing-platforms.md): How Ptally compares with established insurance pricing and rating platforms and with newer AI-led options, on upfront cost, implementation, use of AI, model readability and time to launch.
- [Building insurance pricing models from US rate filings](https://ptally.ai/blog/building-pricing-models-from-us-rate-filings.md): How US rate and rule filings can be turned into working, tested pricing models: what a filing contains, where to find it, how AI speeds up extraction, and the limits to plan for.
- [AI in insurance pricing: from rating guide to live model in days](https://ptally.ai/blog/ai-insurance-pricing-rating-guide-to-live-model.md): How AI is changing the way insurers and MGAs build, test and launch pricing models, and why the best results come from pairing AI with experienced pricing consultants.
- [AI in insurance: where it delivers value today](https://ptally.ai/blog/ai-in-insurance-where-the-value-is.md): A practical guide to where AI creates measurable value across insurance, from pricing and underwriting to distribution, claims and operations, and what successful projects have in common.
- [The benefits of AI in regulated industries, and why explainability comes first](https://ptally.ai/blog/ai-in-regulated-industries-explainability.md): How insurers and other regulated firms can benefit from AI while meeting expectations on fairness, transparency and accountability from regulators such as the FCA, NAIC and EU.
- [AI for insurance distribution: pricing in every channel](https://ptally.ai/blog/ai-for-insurance-distribution.md): How AI is changing insurance distribution, from aggregators and embedded insurance to conversational quoting and AI agents, and why a real-time, explainable pricing engine is central to all of them.
- [Why insurance pricing models should be human readable, especially when AI writes them](https://ptally.ai/blog/human-readable-pricing-models.md): As AI drafts more insurance pricing logic, the format of the model becomes a control. This article explains why declarative, readable pricing models are faster to review and audit than generated code.
- [Every rate change needs a test suite: regression testing for insurance pricing](https://ptally.ai/blog/testing-insurance-pricing-models.md): How to regression test insurance pricing models: building test cases from worked examples, covering declines and referrals, and checking every rate change before release.
- [How much does an insurance rating engine cost? Licences, implementation and pay as you write](https://ptally.ai/blog/how-much-does-an-insurance-rating-engine-cost.md): The real costs of an insurance rating engine: licence fees, implementation projects, internal team time, rate changes, hosting and the cost of delay, and how the main commercial models compare.
- [Using Claude and ChatGPT to build insurance pricing models: what works and what doesn't](https://ptally.ai/blog/using-claude-and-chatgpt-to-build-pricing-models.md): A practical guide to building and editing insurance pricing models with AI clients such as Claude and ChatGPT over MCP: where they help, where they struggle, and how to keep people in control.
- [The EU AI Act and insurance pricing: what high-risk means in practice](https://ptally.ai/blog/eu-ai-act-insurance-pricing.md): The EU AI Act treats AI used to assess risk and price life and health insurance for individuals as high-risk. This article explains what that means for pricing teams and the controls worth putting in place across all lines.
- [How to price pet insurance: rating factors and a worked example](https://ptally.ai/blog/how-to-price-pet-insurance.md): The main rating factors in pet insurance, how they combine into a premium, and a worked example priced by a real rating model, from base rate to Insurance Premium Tax.
- [Launching an MGA: getting your first product priced and live](https://ptally.ai/blog/launching-an-mga-pricing.md): A practical guide for new MGAs on taking a first product from rating guide to live quotes: capacity partners, model build, testing, distribution channels and monitoring rates after launch.
- [Consumer Duty and pricing models: how to evidence fair value](https://ptally.ai/blog/consumer-duty-pricing-fair-value.md): What the FCA's Consumer Duty and general insurance pricing rules mean for pricing teams, and the evidence to keep so you can show your prices offer fair value.
- [What to look for in an insurance pricing platform: a buyer's checklist](https://ptally.ai/blog/insurance-pricing-platform-buyers-checklist.md): A practical checklist for insurers and MGAs choosing a pricing platform, covering model build, testing, versioning, explainability, APIs, AI and MCP, performance, commercial terms and support.
- [AI agents will buy insurance. Is your pricing ready?](https://ptally.ai/blog/ai-agents-buying-insurance.md): As AI agents start comparing and requesting insurance quotes for customers, pricing engines need clear schemas, consistent results, explicit decisions and explanations. What insurers and MGAs should prepare now.
- [Rate changes without the risk: a step-by-step process for pricing teams](https://ptally.ai/blog/insurance-rate-change-process.md): A step-by-step process for making insurance rate changes safely, from analysis and draft versions to testing, approval, release and monitoring, and where AI fits in.
- [The NAIC AI model bulletin explained for insurers and MGAs](https://ptally.ai/blog/naic-ai-model-bulletin-explained.md): What the NAIC model bulletin on the use of AI systems by insurers expects, how it applies to pricing and underwriting, and what MGAs and technology vendors should prepare.
- [Replacing a spreadsheet rater: when to move and how to do it safely](https://ptally.ai/blog/replacing-a-spreadsheet-rater.md): Signs that an Excel rating model has reached its limits, the risks of keeping it, and a step-by-step migration that uses the spreadsheet's own results as tests.
- [Pricing for price comparison websites: latency, volume and fair pricing rules](https://ptally.ai/blog/pricing-for-aggregators.md): What insurers and MGAs need from their pricing to quote on price comparison websites: fast responses at peak volume, consistent prices across channels, thorough testing, fair pricing rules and ongoing monitoring.
- [Human in the loop: designing AI approval workflows for regulated pricing](https://ptally.ai/blog/human-in-the-loop-ai-pricing-approvals.md): How to design approval workflows when AI agents help build and change insurance pricing models: who can draft, approve and publish, what reviewers should see, and how to handle urgent changes.

## Platform guides

- [Getting around Ptally: projects, versions and quotes](https://ptally.ai/blog/getting-around.md): A tour of the Ptally platform: the projects list, a project's page, a version's model, steps and tests, and where to find quotes, the API and MCP.
- [Price a quote: dry runs and live quotes](https://ptally.ai/blog/price-a-quote.md): How to price a quote from a project or version page in Ptally, the difference between a dry run and a live quote, and how to copy the request as a curl command.
- [Run and read tests](https://ptally.ai/blog/run-tests.md): How to run a version's test suite in Ptally, read the results, open a test to see its inputs and expected result, and add tests to a draft.
- [Edit a model in a draft version](https://ptally.ai/blog/edit-a-model.md): How to make changes to a pricing model in Ptally: create a draft version, edit a step or rate table, upload a model or CSV, and summarise the change for reviewers.
- [Approve and publish a version](https://ptally.ai/blog/approve-and-publish.md): How a Ptally version moves from draft to approved to published, what each status means for live quotes, and where to see the version history.
- [Analyse quotes](https://ptally.ai/blog/analyse-quotes.md): How to use the Ptally quotes page: volume, latency, result and validity charts, filtering by project and version, searching quotes and opening a quote's full detail.
- [Manage users and API keys](https://ptally.ai/blog/users-and-api-keys.md): How to add users, understand roles, find and rotate your API keys, and read the audit log in Ptally settings.
- [Connect an AI client and find the API reference](https://ptally.ai/blog/connect-an-ai-client.md): How to use the MCP and API pages inside Ptally to connect Claude, ChatGPT or Cursor, and to find every API endpoint with examples.

## Optional

- [Status](https://ptally.ai/status): Service status.
- [RSS feed](https://ptally.ai/blog/rss.xml)