WTW Radar is a good fit for insurers with an established pricing team that wants analytics, price optimisation and real-time rating in one suite, especially in competitive personal lines such as UK motor and home. Swallow is a good fit for insurers and MGAs that want a rating engine for live quoting, with readable, tested models and AI in the build. If your priority is building and optimising prices from your own data inside a single analytics suite, Radar is worth a close look. If it's getting a product live and keeping rate changes quick and controlled, look at Swallow.
WTW Radar in brief
Radar is the pricing and rating software from WTW (Willis Towers Watson). WTW calls it "an end-to-end solution for rules, analytics, and model deployment" and says it is "trusted by more than 500 insurers globally". The suite covers modelling, optimisation and, through Radar Live, rate delivery, and sits alongside WTW's Emblem modelling software.
Radar Live is the real-time rating engine, with a long track record in UK personal lines. Ageas UK uses it for motor pricing, handling millions of quotes a day and responding to market moves on price comparison websites. WTW also sells Radar Live as SaaS. IMT Insurance in the US took up Radar Live SaaS in 2022 as one rating engine for its property and casualty lines, and Thimble, a US small business MGA, chose Radar Live for commercial lines pricing in March 2026.
Radar has supported Python since version 4.14 in 2022, and in September 2024 WTW added real-time execution of Python models in Radar, with access to more than 8,000 Python libraries.
For AI, WTW launched Radar Vision, an AI-driven performance monitoring tool, in 2025. Radar 5, released in October 2025, added generative AI so users can ask Radar Vision questions in free text, along with machine-led modelling, browser-based cloud hosting and Radar Fusion for commercial underwriting.
WTW has published integrations with Guidewire PolicyCenter and Sapiens. It doesn't publish pricing.
Swallow in brief
Swallow is an AI-powered pricing platform and rating engine for insurers and MGAs. Each model is a plain JSON file of ordered steps: inputs, rate table lookups, calculations, transforms, exclusions, refers, excesses and endorsements. Every version carries its own tests and goes from draft to approved to published, with each step logged. The same engine prices quotes over a real-time API, through embedded forms and in voice and chat, and is built to scale to millions of quotes a day. Models cover lines from pet and fleet to property, cyber and US filed programmes.
At a glance
| Swallow | WTW Radar | |
|---|---|---|
| What it is | AI-powered pricing platform and rating engine | Pricing analytics, optimisation and rating suite, with Radar Live for real-time rating |
| Typical buyer | Insurers and MGAs of any size | Typically insurers with in-house pricing teams; strong in personal lines |
| Analytics and optimisation | Not the focus. Swallow implements rating structures designed elsewhere | Core strength: GLMs, machine learning, optimisation and monitoring |
| Where models come from | Rating guides, Excel raters, US rate filings or any modelling tool | Built by your team in Radar, Emblem or Python |
| Model format | Readable JSON of ordered steps, with tests on each version | Vendor specific, with Python models supported |
| Testing | Tests on every version, expected against actual, bulk CSV runs | Impact analysis and monitoring; detail varies by setup |
| Approvals and audit | Draft, approved, published; approvals by role; every quote records its version | Governance for deployed models described; detail not published |
| AI | AI first drafts and tests; MCP server for Claude, ChatGPT and Cursor | Radar Vision monitoring; generative AI queries in Radar 5; machine learning in modelling |
| Channels | Real-time REST API, embedded forms, voice and chat | Radar Live real-time rating; Guidewire and Sapiens integrations |
| Commercial model | Talk to us | Not published; typically a licence and an implementation project |
Where they differ
How much of the pricing process each covers
Radar spans most of the pricing process: analysing data, fitting models, optimising prices, deploying and monitoring them. That reach is why it's common in competitive personal lines. Swallow goes deep on a narrower stretch: turning a designed rating structure into a production model, testing and approving it, serving quotes and handling rate changes.
Who does the building
Radar is made for pricing analysts and actuaries who model and deploy rates themselves, usually with WTW or a partner helping with the first build. On Swallow your team can build models on the drag-and-drop canvas, edit the JSON or work with an AI client. If you'd rather hand it over, send us your rating guide, spreadsheet or filing and we'll talk you through getting it live.
Reading and checking a model
A Swallow model is configuration that an underwriter, actuary or auditor can follow step by step. Each test is a full set of inputs with the result you expect, and the dashboard shows expected and actual side by side, so you can see exactly which quotes a rate change moves. A debug trace shows every input, lookup and formula behind a quote, and every quote records the version that priced it. Rate tables upload and download as CSV, and the whole model downloads to Excel for anyone who wants to check it offline.
What AI is used for
WTW puts AI mainly into analytics and monitoring: machine-led modelling, early signals on inflation, competitors and claims from Radar Vision, and free-text questions in Radar 5. Swallow puts it into building and maintaining the production model: a first draft from a description and spreadsheet, tests generated from a prompt, and governance reports and version summaries for reviewers. Through the MCP server, Claude, ChatGPT or Cursor can learn the format, draft a model, validate it and run its tests. They can't create, edit or publish a project. A person uploads, approves and publishes.
Cost and the road to a first quote
WTW doesn't publish Radar pricing, so ask for the full cost up to the first live quote. For Swallow pricing, talk to us.
Pick WTW Radar if
- You have an established pricing team that wants modelling, optimisation, deployment and monitoring in one suite.
- You compete on price comparison websites and want demand modelling and optimisation alongside the rating engine.
- You want a long-established vendor with a large personal lines user base, particularly in the UK.
- Your team models in Emblem or Radar today and wants to stay in one suite.
Pick Swallow if
- You're an MGA or insurer launching or moving a product and want a rating engine your team can run day to day.
- Your rates come from a rating guide, spreadsheet or filing, or from a modelling tool you already use.
- You want models people can read and audit, with tests on every version.
- You want general AI clients helping to build models, with people approving and publishing every release.
Next steps
Walk through a complete Swallow model on the developer page, see how quotes are priced through the API, or get in touch. Launching a new product? Starting an MGA covers the route from rating guide to first live quote, and our comparison of Swallow and other insurance pricing platforms looks at the wider market.
Based on publicly available information as of November 2026. Vendor offerings change and vary by customer, so confirm current details with each vendor.
