SelectedWork

Brand, website, and AI — shipped in two-week sprints.

Food & Beverage40% fewer calls. 200+ questions handled weekly by AI.

Ember Kitchen

RestaurantBrand Identity / Website / AI Chatbot / Review Responder2026
40%Fewer phone inquiries200+Menu questions handled weekly
Travel & Hospitality3x more enquiries. 15+ hours saved weekly.

Meridian Travels

TravelBrand Identity / Website / AI Trip Planner / Content Engine2026
3xIncrease in enquiries15+Hours saved per week
TechnologyOnboarding: 40% → 78%. Support tickets down 55%.

Stackline

SaaSBrand Identity / Landing Page / AI Onboarding / Support Chatbot2026
78%Onboarding completion55%Fewer support tickets

Lab

AI research and experiments running right now.

Voice Agent Latency

Testing

Benchmarking sub-200ms response times for real-time voice agents — the threshold where callers stop noticing they are talking to AI.

VapiClaude APIVercel Edge

RAG Accuracy Scoring

Live

Automated pipeline measuring how accurately chatbots retrieve and cite the right information from client knowledge bases.

Supabase VectorClaude APIpgvector

AI Content Quality Gate

Prototype

A scoring layer that checks AI-generated content against brand voice, factual accuracy, and SEO signals before it goes live.

Claude APINext.jsZod

Recommendation Engine v2

Testing

Hybrid collaborative + semantic filtering for e-commerce and content platforms.

EmbeddingsSupabaseNext.js

AI Lead Qualifier

Live

Conversational lead scoring that rates prospects during chat based on intent signals, budget indicators, and industry fit.

Claude APIWebhooksResend

Multi-Model Routing

Testing

Intelligent routing layer that picks the right model for each task — optimising cost and latency per request.

OpenRouterClaude APIGPT-4o

Automated Review Responder

Live

Monitors Google reviews and drafts on-brand replies within minutes. Adapts tone per rating — empathetic for 1-star, grateful for 5-star.

Google Business APIClaude APIn8n

Semantic Search Benchmark

Testing

Comparing vector databases for sub-50ms semantic search on large product catalogues.

pgvectorPineconeQdrant

AI Onboarding Flow

Live

Adaptive onboarding that detects where users get stuck and intervenes with contextual help.

Claude APISupabaseAnalytics

Booking Agent

Prototype

End-to-end reservation handling via chat — checks availability, suggests alternatives, and sends confirmations.

Claude APICal.comResend

Document Intelligence

Testing

PDF parsing pipeline that extracts structured data from invoices, contracts, and compliance documents.

Claude VisionZodSupabase

AI Compliance Engine

Live

EU AI Act risk classification and compliance report generation. Powers Irvo — from gap analysis to PDF export.

Claude APISupabaseStripe

Workflow Automation Hub

Live

Orchestration layer connecting AI agents to business tools — event-driven triggers that fire the right AI at the right moment.

n8nMakeWebhooks

Prompt Regression Testing

Prototype

CI pipeline that catches prompt regressions before new model versions reach production.

Claude APIGitHub ActionsVitest

Real-Time Site Auditor

Live

The free audit tool on this site. Fetches real HTML, extracts metrics, and feeds them to Claude for grounded scoring.

Claude APINext.jsHTML Parsing

Streaming Chat Architecture

Live

Server-Sent Events streaming with dual-provider fallback. The chat widget on this site is the live implementation.

SSEClaude APIOpenRouter

Ready to build?

Start a sprint