Prototype & Develop
Turn technical ideas into working proofs of concept, prototypes and production systems.
Applied engineeringSoftware & hardwareData & sensors
Making
technology
work.
We build what you need, connect what you have and fix what is not working. Practical engineering across software, hardware, sensors and data.
Our services
Build. Connect. Recover.
From first prototype to production integration, we provide hands-on engineering for problems that need more than an off-the-shelf solution.
Build & Integrate
Develop software, hardware and data systems that fit your existing workflows and infrastructure.
Discover & Reuse
Extract value from underused data, sensors and equipment through search, analysis and integration.
Rescue & Improve
Recover troubled software projects, including AI-generated code, and improve architecture and reliability.
The founders
Technical depth. Practical delivery.
Two engineering founders with experience across research, industrial systems, software, data and technical leadership.
Co-founder
Paul Bellette
Technical consultant working in GPU computing, machine learning, optimisation and engineering systems.
More about PaulCo-founder
Kristian Weegink
Engineer working across systems and control, software, data, engineering analysis and technical strategy.
More about KristianHow we help
Problems we can help solve.
Sensors into systems
Put lidar, cameras and other sensors to work with tailored processing, analysis and software integration.
SensorsSoftwareIntegration
Searchable information
Connect fragmented documents, email, spreadsheets and datasets for search, classification and decisions.
DataSearchClassification
Software recovery
Audit, repair and restructure fragile or AI-generated code so a promising prototype can become a reliable system.
ArchitectureReliabilityDelivery
Latest writing
Ideas from our engineering work.
16 Oct 2026
Have you ever tried to teach an LLM to balance a stick with words?
Using a tiny LLM to balance an inverted pendulum with words.
15 Sept 2026
Neural network optimisation for sparse deconvolution
Using PyTorch to learn a waveform dictionary and recover spike timings from extracellular neural recordings.
14 Sept 2026
Splatting Lidar Scans
Reconstructing a surface from a Lidar scan and resampling with oriented splats
Let’s build what’s next
Have a technical problem?
Whether you need a prototype, a specialised integration or a rescue plan for existing software, tell us what you are trying to achieve.
