Excessive Agency is the vulnerability that enables damaging actions to be performed in response to unexpected, ambiguous or manipulated outputs from an LLM, regardless of what is causing the LLM to malfunction. Common triggers include: hallucination/confabulation caused by poorly-engineered benign prompts, or just a poorly-performing model; direct/indirect prompt injection from a malicious user, an earlier invocation of a malicious/compromised extension, or (in multi-agent/collaborative systems) a malicious/compromised peer agent. The root cause of Excessive Agency is typically one or more of: excessive functionality; excessive permissions; excessive autonomy. Excessive Agency can lead to a broad range of impacts across the confidentiality, integrity and availability spectrum, and is dependent on which systems an LLM-based app is able to interact with.

Panic Driven Development (PDD)The abandonment of good development practices by a company or individual in order to react to a perceived external threat or future risk. Example: "We started a PDD cycle because other companies are using AI to get ahead of us."

James Pearce shares a practical framework for testing AI products by making them more verifiable, measuring risk clearly, and learning safely from production.

On the 15th of January 2026 myself and Ujjwal Kumar Singh joined a call and pressed record. We were curious to see what would happen. A few weeks later I’d done the same with Neil Taylor and Clare ...

A collection of what I snapped on the day of Leading With AI.I turned them into a Gif with a Claude Gif Maker Skill.

I went to LWAI in London on Friday last week, really enjoyed Nicks talk on Given AI - When steps are scripted - Then humans have controlToday I've been trying to implement some of these ideas creat...

AI has changed everything but there are key aspects of our work like shifting left and right and risk based assessments that remain as relevant (if not more) than before. There is a lot of uncertai...

What my life was lacking was a new test related pyramid. But on a sunny Friday afternoon in Charing Cross, James Pearce's excellent talk on engineering quality into AI based products provided me wi...

I attended the Leading with AI MoT workshop today.What felt good was the reminder that we're all on a journey. It is an incredibly safe, open, and non-demanding space where people come together to ...

Great learnings today at Leading with AI in London! I really enjoyed James' examples to better understand testing an AI chatbot, the variety in outputs and the fun way we can learn about it.&n...

Great advice from James Pearce: no matter what you do, make sure you either win or learn, sometimes, the learning is even more important than the win.

AI is not replacing engineering, AI is changing engineering - Preeti GuptaWin or learn - James Pearce