Cross-Sell Recommender

Surface the next-best services to offer a family-office relationship, combining a deterministic rule layer with an AI re-ranking pass — so every recommendation is explainable and auditable.

When to use

Reviewing a relationship for white space and revenue opportunities.
Preparing an account plan or QBR.
Feeding a proposal drafting step ([[proposal-generator]]).

Inputs

A current [[family-office-profile]] (structure, asset mix, jurisdictions, pain points).
The catalogue of services you can offer and their eligibility criteria.
Existing services already in place for the relationship.

Steps

Run the rule set against the profile to find eligible-but-unused services; each hit carries a rule_id and the profile facts that triggered it.
Score candidates by fit, urgency and estimated value.
Re-rank with an AI pass that weighs qualitative context (stated mandates, timing).
Attach a plain-language rationale to each recommendation citing the triggering facts.
Drop any recommendation that cannot be traced back to a rule or profile fact.

Output

A ranked list of recommendations, each with: service, rationale, rule_id/source, estimated value and suggested next action.

Presenting results

Present every result as one or more clear Markdown tables — one per section, each with a short heading.
Keep prose minimal; put the substance in the tables.
Offer the user a downloadable PDF (formatted) and CSV (the underlying rows), and generate them when asked.
Never invent figures. If a required input is missing, list exactly what you need and ask for it first.