Alongside a website
Customer logins, bookings, payments, quote calculators and secure document exchange. We built a client portal for a Sydney law firm and a measure-and-quote calculator for a shutters business alongside their websites. Estimated in days and quoted in writing before we start, from $1,222 AUD$850 USD per day.
AI and automation
AI product builds
We take an idea and ship a paying product: backend, frontend, mobile, billing, observability, and the LLM glue that makes it real. From $46,631 AUD$32,450 USD.
Automation retrofits
Already have a SaaS or internal tool? We add AI where it earns its keep, like email triage, support deflection, content generation and structured extraction, without rewriting everything. From $24,861 AUD$17,300 USD.
AI infrastructure
LLM gateways, prompt versioning, evals, queue workers, billing plumbing and observability: the layer that decides whether your AI feature stays up at 3am. From $29,028 AUD$20,200 USD.
Discovery sprint first
Every AI engagement starts with one week at $4,500 AUD$3,132 USD: we map the workflow, build an evaluation set from your data, and fix the scope and price. Credited in full against the build.
How an AI engagement works
Brief to scope in 48 hours. Tell us the workflow or product in two paragraphs. We come back with what ships in sprint one, the stack, and the cost.
Sprint one: a demo in 1–2 weeks. The smallest thing that proves the idea works, deployed and clickable, so you can decide whether to continue.
Iterate, weeks 3–8. Each sprint adds one feature that earns its keep, with daily written updates and a weekly live demo.
Our own products
The same engineering runs 7 products of our own. A few of them:
BrightPath
Personalised K-12 online school with an AI tutor named Pax and progress tracking that nudges kids.
Read the story → AI · ContentGhost Writer
Content engine that finds trending topics, writes articles, runs layered quality checks and publishes to LinkedIn and Medium.
Read the story → AI · Social mediaPost Reel
Social scheduler with an AI video studio: give it a URL and it writes a script, voices it, and produces a short video scheduled across platforms.
Read the story →See all our products and client work →
Frequently asked questions
What stack do you build on?
Python (FastAPI, Django) and Node.js (Fastify, Express) on the backend; Next.js, React, and React Native on the front; PostgreSQL and Redis for state; n8n for orchestration; Stripe for billing; LiteLLM for routing across model providers; Docker everywhere.
Do you only build with Claude?
No. We default to Anthropic Claude because it punches above its weight on long-context and structured tasks, but we route through OpenRouter and LiteLLM so projects can pick Gemini, OpenAI, or open-weights when the economics or latency demand it.
How fast can you ship?
First demo in 1–2 weeks for most builds. We move fast because we’ve already built the boring parts (billing, auth, LLM routing, observability) and reuse them across every project.
How does an AI engagement start?
With a one-week Discovery sprint at $4,500 AUD$3,132 USD: we map the workflow, build an evaluation set from your data, and fix the scope and price. It’s credited in full against the build.