> For the complete documentation index, see [llms.txt](https://docs.peakcommerce.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.peakcommerce.com/product/getting-started/meet-mango.md). # Meet Mango Say hello to **Mango** — the clever mongoose who lives inside PeakCommerce and helps you build. Mango hails from the shores of Hawaii, has a bottomless appetite for problem-solving (and for ripe mangoes from the island hills), and a real talent for turning *"I wish I could just describe what I want"* into something working on your screen. She's mischievous enough to be fun, but **veracious** where it counts: Mango always shows you exactly what she's about to do and waits for your okay. She proposes — you decide. Here's Mango in a playful mood: {% embed url="" %} ## What Mango can do Wherever you see a **Create with Mango** button or a **Chat** panel, Mango is ready to help: * **Build components from a description.** In the [component editor](/product/using-peakcommerce/templates/creating-a-component.md), tell Mango *"a three-tier pricing table with a highlighted middle plan"* and she generates a working component — fields, layout, and code — for you to refine. * **Design pages.** In the page designer, describe the page (or the change) you want and Mango assembles it from your components. * **Draft rules.** On the Rules & Automation engines — Business Rules, Pricing Rules, and the rest — describe the behavior (*"15% off annual upgrades"*) and Mango drafts the rule for you to review. * **Answer your questions.** Stuck on something? **Ask Mango** from the help docs and she'll point you to the right place. ## How to work with Mango * **Create with Mango** — the button on the editors and the rule engines. Describe what you want; Mango builds a first draft you can keep refining. * **Chat** — the Chat tab in the component and page editors. Ask for a change in plain language; Mango proposes an edit you can **accept, reject, or refine** — and every decision is recorded, so your team can always see who changed what and when. ## Ask Mango anywhere in the app Administrators also get Mango as a **floating bubble** that follows you throughout the admin app. Open it on any page and ask a question the way that suits you — **type it in chat, or just talk**: Mango converses by voice too (powered by ElevenLabs conversational AI), so you can think out loud while you work. What makes this Mango special is that she answers from **your own tenant's data**, not generic documentation: * **Catalog and pricing** — your product catalog, plans, charges, and plan pricing, so *"what does the annual tier of our advanced plan cost?"* gets a real answer. * **Journeys** — your configured [journeys](/product/journeys-and-pages/journey-basics/journeys-overview.md), their steps, routing, and the commerce actions on each step — handy for *"why does our cancellation flow skip the offer step?"*-style questions. * **Live journey activity** — recent journey-session activity in aggregate (statuses, outcomes, where sessions are in the flow). Customer identity and captured form data are **deliberately excluded** from what Mango can see; for individual-customer investigations she'll point you to the journey's session view in the app instead. * **Retention analytics** — cancellation and save-rate figures computed from the very same source as the app's **Retention** analytics tab, so Mango's numbers can never disagree with what's on your screen. Two things to know about how this is built: * **Strictly read-only.** Mango's in-app knowledge tools can look things up but can never change anything — she can explain and diagnose your configuration, but plans, journeys, and rules stay exactly as you left them. At worst a confused question gets a wrong answer, never a wrong action. * **Tied to you.** Each conversation is bound to your tenant and your user, so if you later contact support about the same issue, the team can see the context and pick up where Mango left off. ## Mango always asks first Mango is quick and a little cheeky, but she never goes rogue. Every change she suggests is a **proposal you approve** before it takes effect — so you get the speed of an eager problem-solver with a human always in the loop. Clever, hungry, and honest to the core. 🥭 --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.peakcommerce.com/product/getting-started/meet-mango.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.