KYC Onboarding Review
Use when reviewing a client or investor onboarding packet to inventory documents, extract KYC fields, apply the firm's KYC/AML rules grid, propose a customer risk rating, and assemble an escalation packet for compliance and attorney review.
When to use
- A user says "run KYC on this new client," "review this onboarding packet," or "screen this investor for onboarding."
- A new client or investor is being onboarded, or a periodic KYC refresh is due.
- A firm needs a structured first-pass file before a compliance officer makes a customer-acceptance or risk-rating decision.
- An onboarding analyst needs to organize identity, ownership, control, and source-of-funds information against the firm's rules grid.
Required inputs
- Onboarding document packet: the actual documents — uploaded or pasted. This typically includes identity documents, entity formation documents, ownership and control documents (UBO declarations, org charts, registers, resolutions), address proof, source-of-funds or source-of-wealth evidence, and tax forms. If no packet is provided, stop and request it.
- The firm's KYC/AML rules grid or CDD policy: the actual firm document setting out the due diligence rules, required documents by customer type and risk level, and the risk-rating methodology. If not provided, stop and request it. Do not construct rules or document requirements from model background knowledge.
- High-risk jurisdiction list and risk-rating methodology (if maintained separately from the rules grid).
- Screening results (optional): sanctions, PEP, and adverse-media results for each named party, if a screening run has been completed. The skill does not perform live screening; it organizes and reviews results that are provided. If no screening has been run, note that screening is pending.
- Customer context: applicant type (individual, entity, trust) and the nature of the intended business relationship.
If the packet or the rules grid is missing, stop and request it. If documents are too incomplete to enable meaningful extraction, ask targeted follow-up questions.