> For the complete documentation index, see [llms.txt](https://partner-docs.covergenius.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://partner-docs.covergenius.com/offers/personalisation-engine/summary.md).

# Summary

#### What is the Personalisation Engine

{% hint style="info" %}
The Offer API is how partners make use of the Cover Genius Personalisation Engine
{% endhint %}

At its core, the Personalisation Engine is designed to be the single, definitive source of truth for what protection offer a customer sees, when they see it, and why.

Cover Genius has built this engine based on our decades plus of experience and is built to be vertical, platform and partner agnostic. Its primary job is to deliver the most relevant and tailored offer to a customer in real time, regardless of whether they are on your website, in a mobile app, or interacting with a marketing campaign. By centralizing the decision-making process, we can ensure consistency and rapidly test new strategies aimed at improving key metrics like conversion rates, retention, and the average value of a subscription or purchase.

The Personalisation Engine is the cornerstone of our digital strategy into the next decade and beyond at Cover Genius.

#### High level flow

When a partner application needs to display an offer for instance, on a checkout page, you would send a single API request to the engine. This request is bundled with crucial Context data (like the user's ID, device type, location, and previous engagement attributes).

You can also send a touchpoint, the place in your customer journey where the offer is sold, such as a checkout page or a product detail page.

The engine then executes a **real-time** process:

1. Evaluate: It takes the provided Context and evaluates it against all available Products and Strategies in our system.
2. Decide: Based on a set of defined eligibility rules and available machine learning models, the engine selects the single optimal Offer for your customer.
3. Respond: The client receives a clean, complete response object called an Offer, which includes all the necessary product details, pricing, and specific content ready for presentation to the customer.
4. Respond: The client receives a clean, complete response object called an Offer, which includes all the necessary product details, pricing, and specific content ready for presentation to the customer. When a presentation profile is configured, the Offer also includes the layout and theme for showing it with **CG Elements**.

This unified approach separates the business logic (what to show) from the display logic (how to show it). The engine decides what to show. The presentation profile on the Offer describes how to show it, and CG Elements builds the offer panel from it. Your client application stays lightweight, which makes testing and deployment of new pricing, content, or layout strategies fast and safe whilst driving growth.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://partner-docs.covergenius.com/offers/personalisation-engine/summary.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
