Skip to main content

AI Assistant

Paid Feature

This feature is only available in paid plans. Learn More

The AI Assistant is a chat-based assistant built into the builder. Users describe what they want — "translate this row to Spanish", "generate a Black Friday hero", "shorten this paragraph and make it friendlier" — and the assistant streams the changes directly into the design.

Screenshot of the Unlayer builder with the AI Assistant chat panel open at the Full Template scope — a prompt to generate a complete email sits in the input, an assistant response is shown, and the canvas in the center shows an email designScreenshot of the Unlayer builder with the AI Assistant chat panel open at the Full Template scope — a prompt to generate a complete email sits in the input, an assistant response is shown, and the canvas in the center shows an email design

The assistant operates at any level of the design tree — full template, row, text, image, and your own custom tools. It also detects the user's locale from their last message, so replies and generated copy come back in that language even if the rest of the editor UI is in English.

Where users find it​

There are two entry points:

  • AI Assistant panel — click the Sparkles button in the editor's top toolbar; a dedicated chat panel slides in on the side, with a persistent thread the user can scroll through.
  • Layer control popover — when a user selects an element, the layer control surfaces a Sparkles button. Clicking it opens the assistant scoped to that selection.
A selected content block on the canvas with the layer-control popover visible, highlighting the Sparkles button that opens the AI Assistant scoped to the selectionA selected content block on the canvas with the layer-control popover visible, highlighting the Sparkles button that opens the AI Assistant scoped to the selection

How it works​

  1. The user types a prompt (and optionally selects an element to scope the request).
  2. The editor sends the prompt and the relevant slice of the design to Unlayer's AI service.
  3. The service streams back text and design operations.
  4. The editor applies design operations as they arrive — the canvas updates live.
  5. The user can stop generation at any time, undo the result, or follow up with another prompt.
AI Assistant chat panel beside a finished, generated Black Friday email — a "Half off. Everything." headline, a short pitch and a Shop 50% off buttonAI Assistant chat panel beside a finished, generated Black Friday email — a "Half off. Everything." headline, a short pitch and a Shop 50% off button

Reliability & uptime​

Unlayer's AI service runs a multi-provider routing layer with an automatic fallback chain — if the primary model is rate-limited, unhealthy, or returns an error, the request transparently retries against a backup model from another provider. Users don't see the retry; the turn just continues. This keeps the AI Assistant working through individual provider incidents instead of going down with them.

Quick start​

The AI Assistant is on by default — a standard unlayer.init is enough, as long as your plan includes it. To be explicit (or to disable it), use features.ai:

unlayer.init({
  features: {
    ai: {
      enabled: true,
      assistant: true, // defaults to true; set false to disable
    },
  },
});

See Setup for the full reference.

What's in this section​

  • How it works — what the assistant does at each scope: full template, row/header/footer, text, image, and custom tools.
  • Setup — enable the assistant in your embed.
  • Pricing — how AI usage is billed.
  • Examples — live demos and starter snippets.
  • Events & Callbacks — track every AI turn and forward it to your analytics pipeline.
  • Customization — pin a specific model and shape the assistant's context.
  • FAQ & Troubleshooting — answers to the most common questions and failure modes.

Privacy & data​

User prompts and the surrounding slice of the design are sent to Unlayer's AI service, which routes the request to one of Unlayer's model-provider subprocessors (currently OpenAI and Anthropic). Inputs are not used to train models. Unlayer logs prompts for short-term debugging and abuse prevention; model providers may apply their own retention windows per their published terms.

For data-handling specifics tied to your contract — data residency, retention, zero-retention agreements, DPAs, or the up-to-date subprocessor list — contact your account manager.

See also: FAQ → Privacy & data and the per-user opt-out pattern in Setup → Disabling per init.

AI can make mistakes. The AI Assistant can produce inaccurate, incomplete, or misleading content. Always review generated copy, links, prices, claims, and translations before sending or publishing. Check important info.