How to Add AI to Framer Sites

Adding an AI chatbot to a Framer site needs no code — you add the embed through Framer's custom-code settings, index your content, and the agent answers visitors from your own pages with citations. It's a natural fit for the designers and founders who ship marketing sites on Framer.

Why Framer sites benefit

Framer sites are usually polished marketing and product sites — features, pricing, FAQs — that visitors have real questions about. An AI agent reads that content and answers in the moment, cited, instead of leaving visitors to scroll. It deflects repetitive questions and captures leads while you focus on design. See the SaaS use case.

Step 1: Index your site

Create an account, get your publishable site key, and point the platform at your published Framer site to crawl your pages. The platform chunks and embeds that content so the agent answers from it accurately. Schedule a re-crawl so updates stay covered.

Step 2: Add the embed via custom code

Framer lets you add custom code in the site settings, with a section for end-of-body code. Paste the AIML.chat embed init there with your publishable key, publish, and the widget loads across your site. No code beyond the paste, and the async embed doesn't affect performance.

Step 3: Configure the agent

Choose a support or sales agent depending on your goal, and give it a grounded prompt: answer only from your indexed content, cite the source, and capture a lead or escalate when it can't help. Grounding keeps answers specific to your site rather than generic — see what is RAG.

Step 4: Match your design

From the widget settings, set appearance and position so the chatbot fits your Framer design. Framer users care about visual polish, so a few minutes of styling makes the widget feel native rather than bolted on.

Step 5: Learn and improve

The analytics show what visitors ask and which questions the agent couldn't answer — a content backlog and a read on what prospects care about. Re-crawl after updating and the agent improves, turning visitor questions into marketing insight.

What you get

Your Framer site now answers visitors instantly with cited responses, deflects repetitive questions, and captures leads — all added with a paste into custom code, no developer required. See Webflow AI chatbot for a comparable platform.

Why grounding beats a generic widget

Whatever platform you are on, the value is not the chat box — it is that the answers come from your own content. A generic chatbot bolted onto Framer will improvise from a general model and confidently get your details wrong, which erodes trust fast. A grounded agent answers only from what you indexed and cites the page, so every reply is traceable to something you actually published. That is the difference between a widget that frustrates visitors and one they come to rely on, and it is why indexing your real content is the step that matters most.

Getting started

Add an AI chatbot to your Framer site on the AIML.chat free plan: index your content, paste the embed into custom code, and configure the agent. Compare tiers on the pricing page.