Cambridge - 25 days ago

LLMs are powering more and more products, but testing their safety, reliability and performance is a significant challenge. Current testing methods are slow, manual and inconsistent, making it difficult for teams to iterate quickly or trust their results. Trismik aims to solve this by using adaptive testing and automatic scoring to evaluate models against a number of dimensions including factual accuracy, bias and toxicity. Inspired by psychometrics and machine learning, the system dynamically selects the most informative test cases, dramatically reducing the number of datapoints required while achieving high reliability and enabling faster development cycles. “AI is no longer just generating answers, it s shaping decisions, products and lives. If we want trustworthy AI, we need to treat evaluation as seriously as we take training. Trismik aims to lead that charge by giving AI engineers the tools to test with precision, act with confidence and build with integrity,” said Nigel Collier, Professor of Natural Language Processing at the University of Cambridge and co-founder and Chief Scientist at Trismik. Collier, who started his career in the 1990s with a PhD in machine translation using neural networks, has increasingly focused on how we can ensure AI acts as a trusted partner to humanity rather than a risk to it. Collier’s curiosity for whether AI could be assessed in the same efficient and fair way as humans, created the genesis for Trismik’s approach to adaptive evaluation. In 2023 Collier met co-founder Rebekka Mikkola, a repeat founder and enterprise sales executive with a passion both for building in AI and opening doors for women in tech. The pair were backed early by Cambridge Enterprise and in 2025 were joined by former Amazon scientist Marco Basaldella as CTO, completing a founding team that blends science, engineering and commercial expertise. Dr Christine Martin, Head of Ventures at Cambridge Enterprise, said: Trismik exemplifies Cambridge’s continued contribution to global AI development with the team combining world-class academic credentials and practical industry experience that has given them the unique authority to define how AI capabilities should be measured. By solving a pivotal challenge in AI adoption, Trismik is positioned to drive trust at scale - we’re excited to support their journey to market. The £2.2m in pre-seed financing was led by Twinpath Ventures, with participation from Cambridge Enterprise Ventures, Parkwalk Advisors, Fund F, Vento Ventures and angel investors from Ventures Together.  Read the full news story on the Cambridge Enterprise website. As AI becomes embedded in everyday tools and decisions, ensuring the safety and reliability of large language models (LLMs) is more critical than ever. Cambridge spinout Trismik has raised £2.2 million to help it make AI testing faster, smarter and more trustworthy. AI is no longer just generating answers, it s shaping decisions, products and lives. If we want trustworthy AI, we need to treat evaluation as seriously as we take training.Nigel Collier, Professor of Natural Language Processing and co-founder of TrismikNigel Collier
The text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright ©University of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms. Yes

Latest News

Hashtags:   

Cambridge

 | 

spinout

 | 

helping

 | 

trustworthy

 | 

Sources