Our Story

Sagitto's founder, George Hill, first started working with artificial intelligence during the 1980s, while developing 'expert systems' within Bank of America in London. On returning to New Zealand, he undertook part-time study with the University of Waikato's Machine Learning Group while working for Hill Laboratories, a well known New Zealand commercial testing laboratory.

This led to the formation of Sagitto Limited, dedicated to combining the power of artificial intelligence, and machine learning, with miniature sensors : sensors small enough to be easily used in the field, rather than requiring samples to be shipped to a laboratory for analysis.

In the menu above, you'll see links to some Case Studies : examples of the Sagitto system being used with our miniature near-infrared spectrometer. The following are examples of broader applications of the Sagitto system.

AI is ideally suited to spectroscopy data.

Pharmaceutical Authentication

While counterfeit or 'fake' drugs get all the headlines, the reality in many countries is that the biggest risk to public health comes from legal but sub-standard drugs. Sagitto has undertaken a project - in conjunction with the Indonesian Pharmacists Association (IAI) - to use miniature NIR instruments and artificial intelligence to detect counterfeit and sub-standard pharmaceutical products.

In many tropical countries it is very difficult to produce antibiotics in the ‘Augmentin’ family. This important class of antibiotics combines both amoxicillin and clavulanic acid as active ingredients , and the latter is very hydrophylic - it loves moisture. Therefore , without good air conditioning systems throughout the manufacturing process, 'Augmentin' type antibiotics can be degraded even before they leave the manufacturing plant. When sub-standard antibiotics are administered to a broad section of the population, the conditions become ideal for development of antibiotic-resistant organisms.

Detecting fake Viagra with miniature NIR

Empowering pharmacists to detect fake and sub-standard drugs.

Honey Authentication

In conjunction with Analytica Laboratories, Sagitto has applied machine learning techniques to metabolomic data from honey samples, in order to identify unique signature compounds to verify the authenticity of Mānuka honey, as part of the UMFHA's ManukaID project.

In this case, Sagitto applied supervised machine learning techniques to data generated by sophisticated laboratory instruments rather than our miniature NIR. Our role in the discovery process was a very important - albeit small - part of a larger scientific research effort.

Using the secure Sagitto web application, UMFHA was able to illustrate the effect of introducing new signature compounds to it's members. By logging in to the UMFHA account on Sagitto's web application, UMFHA members could see for themselves how their own honey samples would be classified using the new signature compounds, once honey testing laboratories started to routinely offer these new tests.

Genuine New Zealand manuka honey contains leptosperin.

DHA, MGO and leptosperin measurements show that this is genuine Manuka honey