Cases
Our own products are the honest test: if the combination of process, AI and software does not work there, we should not sell it to you.
Producing valuable content took a lot of time and effort: keeping up multiple channels, constantly coming up with fresh creative material, and then manually posting it per channel.
An agent that works from a content calendar, develops concepts in dialogue with the team, and automatically prepares and publishes the result.
FIRST VERSION
The first setup worked over email: content for review was delivered, given feedback, and processed. It has since evolved into a solution that automatically puts photos and content online directly.
RESULT
There's now much more time available for reviewing content and responding to comments, because the creative content calendar largely runs on its own — including tighter, consistent styling and brand identity.
BUILT WITH
Python · OpenAI API · Automatisering
Across several websites, enquiries came in through a standard contact form: a name, an email address and a short message. That's where the real conversation had to start, because a colleague still had to figure out what the visitor actually needed, how urgent it was, and what situation was behind the request. Visitors asking a question in the evening or over the weekend got no response at all until someone was available.
We built a lightweight chat widget that shows the same recognisable icon on every website, with a clear “Direct contact” label on hover. Behind the button sits an AI agent that gets its own knowledge source per website: a central, continuously updated knowledge document with that specific brand's services, frequently asked questions and safe conversation boundaries. The agent recognises which piece of context is still missing from the conversation and asks a targeted follow-up question about exactly that, instead of working through a fixed script.
FIRST VERSION
The first version went live with one simple promise: never leave a visitor empty-handed. Without an active AI connection, the widget automatically fell back to a clean, fixed question so a lead was always captured. From there, the setup improved in small steps: first the connection to a real language model, then a richer knowledge document per brand.
RESULT
The chat assistant now runs on four websites, each with its own voice and knowledge, but on the same underlying technology — including a strict “brand identity” rule so the assistant never accidentally starts talking about a different company from the network.
BUILT WITH
PHP · OpenAI GPT-4o-mini · JavaScript · REST
Smaller apps and tools built with Appxperts — each one a working answer to a concrete problem.
APPXPERTS
Trip Inspiration Planner
A web app that takes visitors from picking a destination to a complete, visual day-by-day plan in three simple steps — no booking involved, purely for inspiration.
APPXPERTS
Fleet & Maintenance Tracer
A serverless, interactive city map that shows at a glance what's already been mowed or swept, where vehicles are, and which reports are still open.
APPXPERTS
Context-Aware POS
A point-of-sale system that adapts to time of day and context, so ordering during a rush no longer feels like clicking through a complicated menu.
APPXPERTS
Learning & Onboarding Hub
A visual learning journey with microlearning and a direct buddy pairing, onboarding new employees step by step with visible progress.