Always present
How the client-facing layer works.
Every client question goes through four steps before an answer is delivered. Here’s what happens inside each one.
AI Engine
How every client question is handled
Four steps happen between a client question and a compliant response. Here’s what occurs at each one.
Client question
“Should I be worried about my tech exposure given current market conditions?”
Enters the platform
Step one
Retrieval
The question is matched against your institution’s knowledge base — house view, research, product shelf, and the client’s actual portfolio. Generic AI answers from the open web are excluded.
Step two
Policy check
Before any response is generated, the question is classified against your compliance rules. Is this a suitability trigger? A regulated advice question? Your institution’s policy layer determines what can be answered and how.
Step three
Response generation
The answer is generated using your approved sources, your tone of voice, and your disclosure framework. The client receives a response that sounds like your institution — not a generic AI.
Step four
Logging
Every interaction is logged with full context. Your compliance team has a complete, exportable audit trail for every client conversation — searchable by client, date, classification, or RM.
Delivered to client
Compliant response
Nextvestment · Classified Tier 2 · Compliant
Based on your current portfolio allocation, your tech exposure is 34% — above your stated risk threshold of 25%. Given current market conditions, your house view suggests a cautious position on growth tech. Would you like to review rebalancing options with your advisor?
Timestamp logged
Classified Tier 2
3 sources retrieved
Policy checks passed
Disclosure applied
Audit trail written
Next
Compliance architecture
How every interaction is classified, logged, and audited.