AHOY Labs Scores 74.95 on EnterpriseRAG-Bench, Beats Major AI Players
News related to:AHOY Labs · 2 min read
AHOY Labs, a technology firm based in Montreal, Quebec, has announced its performance on the EnterpriseRAG-Bench, a public, open-source benchmark for enterprise artificial intelligence (AI) systems. The company, which operates under the name Trouvé, achieved an overall score of 74.95, ranking 8th out of 26 systems evaluated in the benchmark. This places AHOY Labs ahead of several major global enterprise AI players.
The benchmark, which simulates a company's archive of over 500,000 documents, including emails, chat threads, files, tickets, sales records, and meeting transcripts, then poses 500 questions. The system's performance is judged on the accuracy and completeness of the answers, as well as the relevance of the documents returned. AHOY Labs' results indicate that, on average, the system returns 1.03 irrelevant documents per answer. In comparison, another major enterprise AI player evaluated in the benchmark returned 15.7 irrelevant documents per answer.
According to Jamil Shinawi, the Founder and CEO of AHOY, the company's focus on precision is a key differentiator.
AHOY's platform is designed to run inside the customer's own premises, on the customer's own hardware. It can operate fully offline, ensuring that sensitive data never leaves the organization. The company's internal testing shows that the platform delivers the same benchmark result when running fully offline. Shinawi emphasized that sovereignty is built into the system itself, not added as a hosting option. "Every AHOY deployment is sovereign," he stated.
The EnterpriseRAG-Bench was published with an accompanying research paper and is open source under the MIT license. AHOY Labs' results are a testament to the company's commitment to delivering accurate and relevant AI solutions for enterprise use.
Founded by Jamil Shinawi in 2018, AHOY is a deep-tech frontier lab and infrastructure company delivering Physical AI. The company's modular stack runs on-chip, at the edge, on-prem, and in hybrid cloud configurations to provide auditable action for cities, transportation networks, utilities, sovereign sites, and other complex operational environments. AHOY's unified platform for building, governing, and deploying Real-World AI, known as AHOY Machine Studio (AMS), is designed to run anywhere from cloud-connected setups to fully offline, air-gapped installations on the customer's own infrastructure.