Humberside Police and Coeus Software have announced the results of an artificial intelligence (AI) trial that could save officers more than 23,000 hours a year, according to new modeling.
The “test and learn” initiative, known as Project Moriarty, looked at how AI can help frontline police officers access accurate and timely procedural guidance when they are out in the field. Funded through the National Police Chiefs’ Council (NPCC) and the National Science and Innovation Board (NSIB), the trial supports the Home Office’s Police Efficiency and Collaboration Program and its efforts to “retain officers in their communities with the information and tools they need to perform their jobs now and in the future”.
The project combined Coeus Software’s secure PoliceBox mobile platform with a new AI-powered assistant named Cecil to provide officers with validated procedural advice based on official police policy, guidance and legislation, without relying on public or external data sources.
Addressing lack of experience on the front lines
Humberside Police said the initiative was in response to one of the force’s most pressing challenges: the declining experience of frontline officers. In March 2024, 35% of police officers in England and Wales had been with the force for less than five years, compared to just 14% in 2016, and voluntary redundancies have also reached record levels.
To bridge this gap, Coeus developed Cecil, a digital mentor within the PoliceBox app. Police officers can ask conversational questions, such as “I was in a traffic accident,” and receive guidance on related procedures within seconds. The system uses a search augmented generation (RAG) AI engine to analyze approved materials and provide answers.
During the trial, officers praised Cecil for its accuracy, relevance, and ease of use.
- Accuracy: 4.6 / 5 (92% rated 4 or higher)
- Relevance: 4.5 / 5 (88% rated 4 or above)
- Ease of use: 4.6 / 5 (84% rated 4 or above)
- Usefulness: 4.4 / 5 (86% rated 4 or above)
Response times averaged between 5 and 20 seconds, with half of all queries answered within 7 seconds.
Humberside Police estimates that if adopted across all forces, Cecil would save more than 23,000 hours of police time a year, the equivalent of bringing several full-time officers back to the front line.
If you like this content…
“Project Moriarty’s trial with Humberside Police demonstrated how the Cecil AI assistant can provide real-time guidance to officers on the ground. Combined with PoliceBox’s ability to digitize frontline policing, it has the potential to transform efficiency and enhance community engagement,” said Simon Hall, CEO of Coeus Software.
“The original Sergeant Moriarty helped define police professionalism and procedural discipline, and our Cecil continues that tradition in the digital age.”
AI as a tool for confidence and consistency
Humberside Police innovation manager Colin Dolling said Project Moriarty showed how AI could enhance police confidence and consistency in real time.
“By putting guidance directly in the hands of police officers, we are helping them make better decisions for the communities they serve,” he said.
A detective constable who took part in the trial added: “It will be very helpful from an investigative point of view because officers will have immediate access to all the data. If officers have information on their devices, it will improve investigative standards.”
Named after Chief Constable Cecil Charles Hudson Moriarty OBE, whose 1920s handbook shaped the standards of professional policing, today’s digital Cecil aims to help officers guide complex operational decisions “with clarity, precision and confidence”.
Middlesbrough-based Coeus Software develops AI-powered mobile solutions for public safety, health and local government. The company’s PoliceBox platform is hosted on the AWS UK Police Assured Landing Zone and enables officers to complete secure digital workflows on their mobile devices while remaining “visible in the community.”
