Forces Claude to answer only from your materials and verified online sources — no inference, no assumptions, no gap-filling. Every claim must be anchored to a cited source.
Meet the Authors
Latest Tools, Skills & Articles
Source-Locked Verification
The Source-Locked Verification skill forces Claude into a strict evidential-fidelity mode where it can only answer from two sources: materials you provide, and online sources it has actually accessed during the task. It cannot infer, assume, estimate, generalise, or fill gaps – if something isn’t expressly stated in the evidence or a verified source, Claude must say so rather than fabricate a plausible-sounding answer.
Using AI in Legal Work: A Practical Verification Framework
Generative AI is already embedded in legal work. Lawyers are using it for research, for drafting, for summarising evidence, for reviewing correspondence. The question of whether the profession should engage with these tools has been overtaken by events. It already has.
AI Governance Risk Radar
AI Risk Radar is a prototype tool that helps identify potential regulatory and compliance risks across six key domains based on your AI system profile.


