Mark Levene
From prompt engineering to prompt programming for providing automation in LLM-based systems
Abstract:
Large language models (LLM) are a generative AI technology that is promising to deliver automation of a
wide range of programming tasks without the needs for detailed programming. Thus, since prompts can be very high-level, LLMs have the potential of providing semi-autonomous behaviour that could be embedded in AI agents.
Here we discuss a novel method, that we call prompt programming, for managing complex tasks to be delivered by LLMs. We propose bounded flowchart logic as a low-complexity, iteration free, programming paradigm for prompt programming, that hides the complexity of the LLM’s implementation in process and decision nodes.
We will then illustrate prompt programing via a case study from the domain of fact-checking, highlighting the benefits that may accrue from using it.
Prompt programming has the potential to transform programming into a higher-level activity. The implications could be wide-spread, however, it requires trust in the ability of the LLM to deliver “high quality” results. Consequently, prompt programming could facilitate the production of safer and more trustworthy AI systems.
Short Bio:
Mark Levene received his PhD in Computer Science from Birkbeck College, University of London,
having previously been awarded a BSc in Computer Science from Auckland University New Zealand.
Following his PhD he was a faculty member in the Department of Computer Science at University College London (UCL). Subsequently he returned Birkbeck College as Professor of Computer Science, where he is a member of the Data Science and Artificial Intelligence research group. His main research interests are: data science; applied machine learning; computational social science; and trustworthy and safe AI. He has published extensively in these areas, and has published books on data science and machine learning, search engine technologies and relational data bases.
Alan Winfield
What could possibly go wrong? A case study in responsible robotics
ABSTRACT:
Robot accidents are inevitable. In this talk I will outline a framework for social robot accident investigation; a framework that proposes both the technology and processes that would allow social robot accidents to be investigated and lessons learned. I shall describe a series of simulated robot accidents and investigations, enacted with volunteers and real robots. And to conclude I will position accident investigation within the practice of responsible robotics and argue that social robotics without accident investigation would be no less irresponsible than aviation without air accident investigation.
Short Bio:
Alan Winfield is Professor of Robot Ethics at the University of the West of England (UWE), Bristol, UK, Visiting Professor at the University of York, and Associate Fellow of the Cambridge Centre for the Future of Intelligence. Alan co-founded the Bristol Robotics Laboratory where his research is focussed on the science, engineering and ethics of cognitive robotics. Alan is an advocate for robot ethics; he chairs the advisory board of the Responsible Technology Institute at the University of Oxford and has co-drafted new standards on ethical risk assessment and transparency.
Samia Nefti-Meziani
Building an ethical future: How robotics and AI are transforming work, health, and sustainability
ABSTRACT:
Key ethical concerns associated with Robotics and AI typically include issues of privacy and surveillance, safety and system reliability, as well as potential impacts on employment and the economy.
However, our project experience shows that these risks are not inherent or unavoidable. In many applications, robotics and AI can enhance ethical outcomes, for instance, by taking people out of dangerous environments, reducing workplace injuries, and enabling more accountable, transparent, and responsible operational practices.
Short Bio:
Professor Samia Nefti-Meziani OBE is Director of the Birmingham Robotics Institute and Chair in Robotics and AI at the University of Birmingham. With more than 25 years of pioneering research, she is internationally recognised as a leading authority in robotics, intelligent automation, and AI. She received the OBE in the Queen’s Jubilee Birthday Honours for services to robotics and was named among Robohub Silicon Valley’s Top 30 Women in Robotics Worldwide.
She has led major UK and EU-funded research programmes supported by EPSRC, Innovate UK and UKRI, advancing robotic technologies across nuclear, aerospace, transport, food manufacturing and healthcare. She is Academic Co-Chair of the UK Cross-Sector Robotics and Autonomous Systems Task Force.
Professor Nefti-Meziani combines technical leadership with a strong focus on the conditions required for the successful deployment and commercialisation of robotics and AI. She has long championed collaboration between engineers, industry leaders and policymakers to accelerate national adoption and secure economic and societal benefit.
One of her most significant contributions is the establishment of the National Committee on Robotics Regulations and Standards, created to bring coherence to the UK’s regulatory landscape. The Committee unites 16 regulators, standards bodies and major infrastructure organisations.
Her collaborative ethos also shapes her leadership of major national initiatives such as the £34.6M RESCu-M² programme, which supports the UK’s transition to a circular manufacturing ecosystem. She has extensive experience directing large-scale and multidisciplinary research efforts, including co-directing the EPSRC National Hub FAIR-SPACE, and has driven major investment in the North of England Robotics Innovation Centre by translating laboratory innovation into practical, industry-ready solutions.
Maria Axente
Beyond principles: Building AI governance that actually works
ABSTRACT:
Short Bio:
Maria is a globally recognised expert in responsible AI, known for bridging the worlds of business, ethics, and policy to help organisations adopt AI wisely and well. Over the past 2 decades she has launched and grown ventures in Eastern Europe and the UK, led AI projects at PwC UK, and guided corporate boards, startups, and governments through complex decisions at the intersection of technology and trust.
Maria serves as an advisor to NATO, UNICEF, the UK Parliament, OECD.AI, and several global standards bodies including IEEE and ISO. She is also a Senior Research Associate at the University of Cambridge (Jesus College), where she explores the societal implications of AI and its governance. She is a passionate public speaker and advocate for AI for Children.
Her insights have been featured by the BBC, Forbes, The Guardian, Business Insider, and the World Economic Forum, where she has authored widely cited frameworks on ethical AI. She is the co-editor of Human-Centered AI: A Multidisciplinary Perspective for Policy-Makers, Auditors, and Users book and the architect behind PwC’s award-winning Responsible AI Toolkit — used across industries to operationalise AI governance at scale.
Maria has been honoured as a LinkedIn Top Voice in AI, a CogX Award Winner for Outstanding Achievement in Ethical AI, Computer Weekly Most Influential Women in UK one of the 100 Brilliant Women in AI Ethics. She founded Responsible Intelligence to bring this expertise directly to the leaders shaping tomorrow’s AI systems.