What we build
Custom builds, off-the-shelf integrations, AI where it earns its place, deterministic automation where it does the job better. The work might be a single Zapier step. It might be a custom agentic team with persistent memory and proper state management.
Below are common patterns. They are illustrative. The right answer for you sits somewhere in this mix.
Public examples
The live examples here are the parts of the work that can be shown openly: websites and web apps. Automation, integrations, and internal AI systems usually sit inside a client's inbox, CRM, accounts package, or private workflow, so the examples further down are written as patterns rather than public case studies.
Full-stack SaaS app
A guest-guide and upsell platform for short-term rental hosts. The full application: secure sign-in, account management, host dashboards, branded guest pages, and SaaS subscription billing through Stripe. Fully managed by us, running fast on low-cost infrastructure.
See it live: welcomedeck.com →
Static marketing website
A wedding celebrant needed to be found locally and trusted at first glance, without a website that demands monthly attention. We built a fast, self-contained site with local search structure and clear enquiry paths. It's live, and it costs almost nothing to keep running.
"Easy to work with, fully understood and respected my requirements. Quick delivery, and fast turnaround on any changes I requested."
Working demos
These aren't client projects. They're live demos we built to be touched: talk to them, push them, and see what custom feels like before you spend anything.
The tool is never the point. The fit is.
AI Systems
Inbound messages, free-form documents, customer questions, judgement calls in the middle of a workflow. This is the work where rules-based automation becomes brittle. We use LLMs, RAG pipelines, and agentic patterns where the cost of being slightly wrong is acceptable. A deterministic alternative would be heavier to build than the problem deserves.
The deep end. Engineering-grade work for problems a single agent or prompt chain can't hold.
Scoped per problem. Larger than a single task, often a defined Custom Software & Automation engagement or a multi-stage implementation.
Automation & Integration
Most of the time the problem isn't "we need AI", it's "the same information has to live in three places and they don't agree". Deterministic automation is faster to build, cheaper to run, and easier to trust than dropping an LLM into the middle of an invoice flow. We pick the platform after the workflow is clear, never before.
Custom Builds
Most SMEs don't need a bespoke product. Some do. Where an existing tool would force the business to bend around it, a small focused build is often cheaper over five years than the workarounds that accumulate around a near-fit SaaS.
Not sure what bucket you fit in?
Most of the work we end up doing started as "I'm not sure if this is even a thing you do." If you can describe the friction in plain English, we can usually tell you within a day whether it's a fit and what it would cost.
The principle, again
We'll tell you when AI is the right answer, and when a single Zapier step does the job better. We'll tell you when off-the-shelf fits, and when custom code is worth the effort. We'll tell you when the problem is automation, and when the real problem is that the underlying process needs cleaning up first.
The deliverable is a system that runs, integrated into your existing ecosystem, documented, with your data and accounts in your name. It lives in your environment, or we run it for you on compliant infrastructure, whichever fits. Whatever underlying tools we used to build it.
