Skip to main content

Prism Intelligence

Detects AI-agent referrers; adapts CTAs and concierge context in real time.

AI Infrastructure·Shipped·Rev. 2026·CF Worker · Edge JS

What is Prism Intelligence?

Prism Intelligence is a real-time visitor intelligence layer that detects referral source at the network edge, classifies it into a channel and topic, and passes that context downstream to adapt CTAs and the AI concierge system prompt. A Cloudflare Worker inspects the Referer header on every inbound request, which avoids the header stripping that breaks server-side detection on many modern frameworks.

Abstract

Prism is a real-time visitor intelligence layer that detects referral source at the edge, classifies it into a channel and topic, and passes that context downstream to adapt CTAs and the AI concierge system prompt. One visitor signal splits into multiple adaptive behaviors — hence the name.

Problem

Most sites serve the same hero copy and call-to-action text to every visitor regardless of how they arrived. A visitor referred from an AI answer engine who just read about a specific topic is in a different mental state than someone who clicked a paid ad or arrived through organic search.

The referral header is often stripped before it reaches server components, and client-side `document.referrer` is an unreliable fallback. A reliable solution needs to capture the signal at the network edge, before any header stripping occurs.

Approach

Edge detection

A Cloudflare Worker runs on the site's zone and inspects the `Referer` header on every inbound request. Detected AI sources (Perplexity, Gemini, ChatGPT, Claude, Copilot, and others) set a short-lived ai_ref cookie with a 1-hour TTL.

A client-side component provides a `document.referrer` fallback for sources where the header survives.

Context resolution

A broader _apex_src cookie (30-day first-touch) tracks all referral channels — organic, paid, social, email, and referral. A resolution function checks both cookies in priority order and returns a typed context object carrying tier, medium, source, and topic.

Tiered adaptation

Full-tier sessions (within 1 hour of arrival) receive channel-specific CTA copy and an enriched concierge system prompt. Light-tier sessions (1 to 7 days) receive only a label swap.

Direct or stale sessions receive no adaptation. All adaptations fire a GA4 event for downstream analytics.

Status

  • Live on isimplifyme.com with both AI and broad-channel detection (v2).
  • Other network sites carry the v1 AI-only variant; v2 rollout follows production validation.
  • Concierge context injection is active on isimplifyme.com.

Frequently asked

I could not be happier with this company! I have had two websites designed by them and the whole experience was amazing. Their technology and skills are top of the line and their customer service is excellent.
Dr Millicent Rovelo
Beverly Hills
Apex Architecture

Every site we build runs on Apex — sub-500ms, AI-native, zero maintenance.

Explore Apex Architecture

Stay Ahead of the Curve

AI strategies, case studies & industry insights — delivered monthly.

K