Fuseideas

Fuseideas is a Boston advertising agency. I built their website as a headless Next.js and WordPress platform.

As generative AI rapidly became central to marketing and search, I proposed adding a conversational assistant to the site to demonstrate Fuseideas' capabilities in this space. The goal was to allow visitors to explore the agency's services and portfolio through natural language rather than relying solely on traditional navigation.

Editors also needed the ability to manage complex pages without engineering support. WordPress manages content through custom ACF-backed Gutenberg blocks, while the Next.js frontend fetches data via GraphQL and renders components through a typed block registry of roughly two dozen custom blocks, with pages statically regenerated on a rolling basis.

Beyond the core site, the platform hosts campaign landing pages, interactive quizzes, an email signature generator, and other internal tools.

AI Assistant Architecture

The assistant uses a custom RAG knowledge layer backed by Supabase. Agency content is flattened, embedded with OpenAI embeddings, and stored in Postgres with pgvector. Each response is grounded through vector search plus a pre-built knowledge cache, so answers come from real work and services rather than generic model output.

To support ongoing maintenance, I built an internal dashboard that allows administrators to index new content and manage the data available to the RAG system.

GPT-4o streams the user-facing response, while a second GPT-4o call runs silently in JSON mode to extract structured signals such as relevant work slugs, capability tags, and suggested follow-ups. These signals drive card rendering and expert routing within the interface.

Conversation history is stored in Supabase and passed into each turn so the assistant maintains session context.

AI Discoverability / AEO

In parallel, I worked on improving the site's AI discoverability. At my digital director's request, I strengthened semantic structure and structured data output to support answer engine optimization (AEO), including improvements to page semantics and JSON-LD designed to make agency content easier for AI systems to interpret and retrieve.