- “Test and Learn” trial explored how AI could support frontline officers with timely and accurate procedural guidance in the field
- Over 23,000 officer hours could be saved annually across a single force, according to preliminary modelling
- Download the Project Moriarty report here: Project MORIARTY - signed.pdf
Middlesbrough, UK: Humberside Police, in partnership with Coeus Software, has completed Project Moriarty, a National Police Chiefs Council (NPCC), National Science and Innovation Board (NSIB), Test and Learn funded trial exploring how artificial intelligence can provide frontline officers with accurate, relevant, and timely procedural guidance from a mobile policing application.
The project directly supports the Home Office Police Efficiency and Collaboration Programme and its mission:
“We’re helping to keep officers in communities, equipped with the information and tools they need to do their job, today and in the future.”
By combining AI-powered procedural support with Coeus Software’s secure PoliceBox® frontline policing platform, the initiative demonstrates how officers can remain visible in their communities while gaining instant access to reliable information, tools, and guidance, addressing one of policing’s most critical modern challenges, outlined below.
Addressing frontline experience gaps with the Cecil AI assistant
As of March 2024, 35% of police officers in England and Wales had fewer than five years’ service, compared with only 14% in 2016. The same year also saw the highest voluntary leaver rate on record, with 72% of those leaving having less than five years’ experience.
These statistics highlight the growing challenge of maintaining operational confidence and consistency as experienced officers leave the service.
To help address this, Coeus Software developed “Cecil”, a conversational AI assistant and digital mentor within the PoliceBox® mobile application. For the trial, Cecil derived its answers from a curated knowledge base of official police policies, guidance, and legislation, ensuring that only verified information is used, with no external or public data sources.
When officers ask Cecil, for example, “I’ve arrived at a road traffic accident”, the AI uses its Retrieval-Augmented Generation (RAG) engine to analyse approved materials and return clear, relevant guidance within seconds.
This provides every officer, regardless of experience, with a mobile digital assistant for everyday policing.
Results of the Project Moriarty AI trial
The trial results deliver on the Home Office mission in measurable ways. Officers rated Cecil highly for accuracy, relevance, and ease of use, confirming its potential to improve both confidence and consistency in frontline decision-making.
Key results:
- Accuracy: 4.6 / 5 (92% rated 4 or higher)
- Relevance: 4.5 / 5 (88% rated 4 or higher)
- Ease of use: 4.6 / 5 (84% rated 4 or higher)
- Usefulness: 4.4 / 5 (86% rated 4 or higher)
- Response times: 5–20 seconds (50% of questions answered within 7 seconds)
Estimated time savings:
If Humberside Police used Cecil to answer 100% of procedural queries, it could save over 23,000 officer hours per year — the equivalent of adding several full-time officers back into frontline service.
By enabling officers to access guidance instantly, officers stay in their communities, reducing time spent searching for information and allowing them to focus on serving the public. This fulfils the Home Office mission by keeping officers in their communities, reducing time spent searching for information, and ensuring they are equipped with the right tools and knowledge to serve the public, today and in the future
“The Project Moriarty trial with Humberside Police showed how the Cecil AI assistant can deliver real-time guidance to officers in the field. When combined with the power of PoliceBox to digitise frontline policing, it has the potential to transform efficiency and enhance community engagement, exactly in line with the Home Office mission to keep officers in communities, equipped with the right tools and information.”
“The original Chief Constable Moriarty helped define policing professionalism and procedural discipline. Our ‘Cecil’ continues that legacy for the digital age, a modern assistant helping officers make confident, consistent decisions wherever they are.” - Simon Hall, CEO, Coeus Software
“Project Moriarty has shown how AI can enhance officer confidence and consistency in real time. By placing guidance directly in officers’ hands, we’re helping them make better decisions for the communities they serve.” - Colin Dring, Innovation Manager, Humberside Police
“I think this would be very useful from an investigation view as it has all the data readily accessible for officers. This would improve investigation standards if they had the information on their devices.” – Trial Participant, Detective Constable, Humberside Police