Classify an AI system under the EU AI Act (Regulation (EU) 2024/1689). Give a plain-language description of what the system does and it returns the risk tier (prohibited / high_risk / limited / minimal), the exact Annex III category where applicable, and the binding Articles — every reference grounded verbatim in the law. USE THIS when the user asks whether an AI system is high-risk or prohibited, what obligations apply to it, or which Articles bind a specific AI use-case. For looking up one known Article use lookup_article; for keyword search use search_eu_ai_act.

Return the verbatim text of one specific EU AI Act Article (1–113), exactly as published in the Official Journal of the EU. USE THIS when the user names or asks for a known Article number (e.g. 'show me Article 6', 'what does Article 5 say'). For keyword/topic search across the whole law use search_eu_ai_act; to classify a system use classify_ai_system.

Full-text keyword search across the entire EU AI Act corpus — all Articles (1–113), Recitals (1–180) and Annexes (I–XIII) — returning the provisions that match your terms, each grounded verbatim in the law. USE THIS when you want to find where a topic, term or obligation is addressed but do not know the Article number (e.g. 'where does the law cover human oversight?', 'find biometric categorisation', 'rules for GPAI'). To fetch one known Article use lookup_article; to assess a specific system's risk tier use classify_ai_system.

Return the canonical EU AI Act application timeline (the staggered dates each obligation starts to apply, reflecting the Digital Omnibus adjustment) together with the penalty/fine tiers under Article 99. Takes no arguments. USE THIS when the user asks when the EU AI Act (or a specific obligation) applies, what the key compliance deadlines are, or how large the fines can be.