The AAIF Community Presents Can Your Agent Prove It? Evidence, identity, and control for agents that use real tools.
Agents can return the right answer for the wrong reason. They skip the approved tool, inherit too much permission, hide retries, or recover by taking a destructive shortcut.
This AAIF Liverpool night asks one question: what evidence is enough to trust an agent with a real system?
We look at tool traces, evaluation signals, identity and policy boundaries, and the controls that make agent actions explainable, containable, and recoverable.
The room is small and technical. Come if you build, operate, or secure agentic or LLM systems, or if you want to see how other people do it.
What We'll Cover
Opeyemi opens with the identity and authority chain behind one agent tool action.
Dr Procheta Sen then covers mechanistic explanation techniques for large language models. We finish with questions for both speakers.
Agenda
17:30 - Doors & Check-in
17:38 - Welcome
17:41 - Talk 1: Babalola Opeyemi Daniel
17:56 - Short Break
17:59 - Talk 2: Dr Procheta Sen
18:24 - Q&A with both speakers
18:28 - Wrap 1
18:30 - Close; informal networking until 19:00
Speakers
Babalola Opeyemi Daniel - Community Event Coordinator, AAIF Liverpool, and a software and AI infrastructure engineer. In "Who Is Acting, and on Whose Behalf?", he follows the identity and authority chain behind one agent tool action. The examples use neutral architecture and synthetic traces. (15 min)
Dr Procheta Sen - Lecturer (Assistant Professor), Department of Computer Science, University of Liverpool. She covers mechanistic explanation techniques for large language models. The talk examines what happens inside a model when it answers. (25 min)
Who Should Come
Engineers who build, operate, evaluate, or secure agent systems should attend. Researchers and technical leaders are also welcome. No prior knowledge is required.
About AAIF
The Agentic AI Foundation (AAIF) is a community dedicated to advancing the understanding and practical application of agentic AI. We bring together engineers, researchers, founders, builders, and AI enthusiasts to explore how autonomous AI systems are designed, evaluated, and deployed.
Through reading groups, workshops, and community discussions, AAIF brings together engineers, researchers, founders, and AI enthusiasts to exchange ideas, challenge assumptions, and learn from one another.
By attending you agree to our Code of Conduct and Privacy Policy.