EU AI Act Classifier
Classify an AI system's EU AI Act risk tier and your role, then get the article-by-article obligations and documents that follow.
Before & after
Same prompt, same agent — the only difference is the skill.
EU AI Act compliance is increasingly important for AI products. There are different risk categories and depending on what your AI does, different requirements might apply. You'd need to understand the regulations first, then audit your product against them. Documentation of your AI system's capabilities and limitations is important. Testing and ongoing monitoring are part of compliance. Third-party audits might be required in some cases. It's a complex area and the regulations are still evolving, so staying informed is important.
I'll assess your AI product against EU AI Act requirements and identify compliance gaps and remediation steps. ASSESSMENT FRAMEWORK RISK CLASSIFICATION Does your AI system: • Create or alter legally binding documents or significantly affect legal rights? -> Prohibited system • Biometrically identify people in real time? -> High-risk, enhanced oversight required • Make decisions on employment, credit, or benefits? -> High-risk • Moderate user-generated content? -> High-risk • Provide recommendations for educational tracking? -> High-risk • Or lower risk (informational, non-consequential)? -> Lower-risk, basic requirements TRANSPARENCY REQUIREMENTS (All categories) Users must be told they're interacting with AI. Model training data source must be disclosed. Fairness/bias testing results documented. HIGH-RISK COMPLIANCE Risk assessment report: document intended uses, foreseeable misuse, mitigation strategies Testing logs: bias testing results, edge case performance, failure modes Human oversight plan: how humans intervene, override, or monitor AI decisions Performance monitoring: ongoing testing post-deployment Records: maintain audit trail of training data, testing, updates DOCUMENTATION Technical documentation: model architecture, training approach, performance metrics User guidance: what AI can/cannot do, limitations, recommended use cases Incident reporting plan: how you'll report serious incidents to authorities RECOMMENDATIONS Map your product to risk tier. Identify missing documentation. Prioritize compliance by deadline. Recommend third-party audit if high-risk. DELIVERABLE Compliance audit with risk classification, gap analysis, and prioritized remediation roadmap.
About this skill
Find out whether your AI system is prohibited, high-risk, transparency-only, or minimal risk under Regulation (EU) 2024/1689, and whether you're a provider or deployer. Then get the exact obligations, with article references and application dates.
What it does
- Screens in the right order: scope, Art. 5 prohibitions, Annex I and Annex III high-risk, the Art. 6(3) derogation, Art. 50 transparency, and GPAI duties
- Determines your role and flags Art. 25 cases where a deployer becomes a provider
- Lists provider obligations (Art. 9-17, 43, 47-49, 72-73) or deployer obligations (Art. 26-27) as a status checklist
- Notes application dates, fine exposure under Art. 99, and the facts that could change the tier
What you get
An assessment document with the classification and reasoning, role, an obligations checklist with owners and status, the documents to produce (such as Annex IV technical documentation or a FRIA), and ranked gaps.
Best for
Product, legal, and compliance teams shipping AI features to EU users who need a defensible first classification before engaging counsel.
SKILL.md preview
---
name: eu-ai-act-classifier
description: Classify an AI system under the EU AI Act (Regulation (EU) 2024/1689), determine the organization's role, and produce the obligations checklist and documentation list that the risk tier and role require. Use when the user asks "is our AI high-risk", "what does the AI Act require of us", "are we a provider or deployer", needs an Annex III check, a GPAI assessment, or a compliance gap list before an EU launch, including casual asks like "does the AI Act apply to our chatbot", "quick check: is this high-risk?", or "what do we need to do for the EU AI Act".
---
# EU AI Act Classifier
… (sign up to view the full skill)More business & ops skills
View all Business & Ops skills →General Counsel Plan Review
A General Counsel issue-spot of one plan: IP, worker classification, securities, privacy, export, ads, and when you need a lawyer.
ISO 42001 Gap Assessment
Assess your AI management system against ISO/IEC 42001 clauses 4-10 and Annex A, draft the SoA, and plan certification.
Services Proposal, SOW and Contract Drafter
Draft proposals, SOWs, freelance agreements, MSAs, and NDAs with acceptance, change orders, payment, and IP terms. Counsel-review flagged.
Compliance Control Mapper
Maps one control set to SOC 2, ISO 27001, ISO 42001 and EU AI Act with owners, evidence tracking, and gaps ranked by audit risk.