ribbons digital

Services

Applied AI, web apps & native Apple software.

Every project starts with your goal, not our stack.

Here is what we build, what you get out of it, and - for your technical people - exactly what it is made of.

What we build

Four ways we earn our keep.

01

Put AI to work in your business

Full Applied AI page

Hand the busywork to software. We build AI agents and workflows that research, draft, summarise, and act across the tools you already use - with guardrails, so you can trust what they do while you sleep.

What you get
  • Hours of manual work automated every week
  • Answers grounded in your own documents, with citations
  • An assistant your team or customers actually use
  • Proof it works before it ships, and monitoring after
For your technical team: the stack
  • Claude / Anthropic Agent SDK
  • Mastra
  • LangGraph
  • Vercel AI SDK
  • Model Context Protocol (MCP)
  • RAG & Vectorize
  • Convex (agent state)
  • TypeScript
02

Launch the product your customers are waiting for

From SaaS products to the internal dashboard that finally replaces the spreadsheet: fast, realtime web apps you can build a business on - without hiring an ops team to keep them alive.

What you get
  • A product ready for paying customers
  • Updates every user sees instantly, no refresh button
  • Internal tools that end the spreadsheet-and-email shuffle
  • One codebase your next hire can pick up in a day
For your technical team: the stack
  • TanStack Start
  • Convex
  • React
  • Tailwind CSS
  • TypeScript
  • Cloudflare Workers
03

Earn a place on the home screen

Native iPhone, iPad, and Mac apps that feel like Apple made them - fast, polished, at home on the platform. When reaching everyone matters more than native depth, we build cross-platform instead and tell you why.

What you get
  • An App Store-ready iOS app
  • A Mac app your team lives in all day
  • iPhone and Android from one codebase when reach wins
  • An honest recommendation on which path fits your product
For your technical team: the stack
  • Swift / SwiftUI
  • iOS
  • macOS
  • React Native (cross-platform)
04

Fast for every customer, everywhere

Your product served from hundreds of cities worldwide, scaling with demand and billed by use. No servers to babysit, no 3am pages, no surprise invoices when you make the front page.

What you get
  • Global speed without a DevOps hire
  • Bills that track usage, not headcount
  • AI features without standing up new infrastructure
  • Deploys measured in seconds, rollbacks too
For your technical team: the stack
  • Cloudflare Workers
  • D1 & R2
  • Durable Objects & KV
  • Workers AI & AI Gateway
  • Vectorize & Queues

Applied AI · in depth

AI that does the work, not just the talking.

Chatbots demo well and then gather dust. We build agents and workflows that plug into your real tools and data - researching, drafting, deciding, and taking action, with guardrails you can trust and receipts you can check.

01

Autonomous agents

Multi-step agents that plan, call tools, and act across your systems - booking, filing, chasing, and reporting back.

02

Workflow automation

Durable pipelines that classify, extract, summarise, and route work the moment it arrives, around the clock.

03

Answers from your data

Grounded answers over your documents and records, with citations - so your team stops digging and starts deciding.

04

Evals & guardrails

Test suites and scoring that measure agent behaviour before and after launch. You see the evidence, not just the demo.

Frameworks & platforms

Anthropic Agent SDK Claude-native agents & tools
Mastra TypeScript agent framework
LangGraph Stateful agent graphs
Vercel AI SDK Streaming UI & providers
Model Context Protocol Tool & data connectivity
LlamaIndex Data & retrieval pipelines
Cloudflare Workers AI Edge inference & AI Gateway
Promptfoo / Braintrust Evals & tracing

Our toolkit

A modern, type-safe stack.

The technical FAQ

For the engineers in the room.

Bring your CTO. These are their questions, answered straight.

What does "Applied AI" mean, and what can you build?

AI that ships into your business, not a demo. Custom agents and workflows wired into your real tools and data: internal copilots, document and research automation, customer-facing assistants, and pipelines that classify, extract, and act. Every build comes with evals and guardrails so you can trust what it does.

Which AI models and SDKs do you build with?

We default to the latest Claude models via the Anthropic Agent SDK and API, and connect tools and data through the Model Context Protocol (MCP). We add RAG / vector search where retrieval matters, and use Convex to manage agent state and orchestration. We are model-flexible when a project calls for it.

Why TanStack Start and Convex instead of Next.js and a separate database?

TanStack Start gives us a modern, type-safe full-stack React framework, and Convex gives us a realtime reactive backend with no separate database, ORM, or websocket plumbing to maintain. The result is less moving infrastructure, end-to-end TypeScript, and realtime by default - so we ship features instead of glue code.

Can you build native iOS and macOS apps?

Yes. We build native apps in Swift and SwiftUI for iOS and macOS when you want the best platform fit and performance. When reach matters more than native depth, we build cross-platform with React Native instead - we will recommend the right tool for your product.

How do you handle data privacy in AI workflows?

We design around data minimisation: scoping what the model can see, keeping sensitive data in your own infrastructure, and using retrieval rather than training on your data. We are transparent about which providers process what, and can architect for region-specific requirements.

Why Cloudflare for hosting and AI?

Cloudflare lets us run code, data, and AI inference at the edge - close to users worldwide - with Workers, D1, R2, Durable Objects, Vectorize, and Workers AI behind one platform. That means low latency, simple global scaling, and AI features without standing up separate infrastructure.

Where are you based, and where do you host?

We are based in Australia and work with clients remotely. We deploy primarily to the Cloudflare edge for low latency everywhere, alongside Convex-hosted backends, and can target specific regions for data-residency needs.

Know what you need? Tell us.

Start a project