29.06.2026

Quartely Workshop 3 2025-26: Bridging AI research with real-world assurance

This June, the SAINTS community gathered for its third quarterly workshop of the year—a dynamic, full-day event dedicated to advancing the frontiers of safe and trustworthy AI. Bringing together SAINTS cohorts, academic supervisors, and industry partners, the workshop served as a vibrant forum for knowledge-sharing, collaborative feedback, and networking.

Spotlight on AI safety, robotics, and trustworthy systems

The day featured a diverse lineup of research presentations showcasing the breadth of talent within the community. Highlights from the event included:

• Cohort 2 Presentations: Researchers from Cohort 2 delivered compelling talks spanning critical domains, including uncertainty quantification, AI safety cases, assistive robotics, and recommender systems.

• Guest Keynote: We were delighted to welcome invited speaker Nigel Rees (Advanced Paramedic Practitioner and Assistant Director of Research and Innovation from the Welsh Ambulance Services NHS Trust), who provided invaluable real-world context with his insights on assuring trustworthy AI in high-stakes ambulance service responses.

• Cohort 1 Showcases: Rounding off the day, Cohort 1 presented a series of rapid-fire lightning talks and an interactive poster session, sparking discussions during the networking intervals.

Perspectives from the cohort

The quarterly workshops continue to be a cornerstone for collaboration, offering researchers a unique platform to bridge the gap between academic theory and industry application. Reflecting on the value of these events, PhD Researcher Austin Long shared:

“At the last quarterly workshop I enjoyed speaking with SAINTS partners, and finding out that many of them have been integrating the same safeguards that I’ve been investigating into real world systems. I’m looking forward to the upcoming SAINTS conference where I may have the opportunity to hear more about their experience with large language models and chain-of-thought monitoring.” — Austin Long, PhD Researcher

With the success of Workshop 3 behind us, the SAINTS community is already looking ahead to the upcoming SAINTS conference, where these vital conversations around large language models, systemic safeguards, and deployment experiences will continue to evolve.

Interested in staying updated on our research and upcoming events? Follow us on social media page or subscribe to updates to learn more about how SAINTS is shaping the future of safe AI.