A private wealth copilot grounded in your own records.

Private wealth teams cannot treat a chatbot as an investment system.

Family offices and VC teams work across PORTFOLIO records, cap tables, INVESTMENT_MEMO notes, POLICY documents, and private DEAL flow like a Series B follow-on diligence. A general chat interface can sound confident about AI infrastructure concentration risk while missing the actual evidence, the IC-approval POLICY, or the access boundary that should gate the answer — and a wrong but polished answer about allocation or diligence status can reach a committee before anyone checks the source memo.

Graph intelligence on ingest

Incoming data becomes queryable graph context.

PORTFOLIO payloads nest HOLDING, COMPANY, INVESTMENT_MEMO, POLICY, and DEAL records as they are imported. RushDB types allocation percentages and status fields on arrival and indexes memo and policy text, so retrieval can pull only approved, portfolio-scoped evidence like memo-northstar-q2 before any prompt reaches the local vLLM endpoint.

Suggested relationship analysis requires an LLM configured for the project. Suggestions stay in draft form until you approve them, so inferred domain meaning never mutates the graph silently. You can also add explicit relationships through the SDK or API.

Data model

One flexible graph for the workflow.

Start with the payload shape your product already produces. RushDB stores it as Records, infers typed properties, and keeps nested or approved domain relationships queryable.

{
  "portfolioId": "fo-2026",
  "strategy": "growth",
  "HOLDING": [{
    "holdingId": "holding-ai-infra-co",
    "allocationPct": 6.8,
    "COMPANY": { "companyId": "northstar-compute", "sector": "ai_infrastructure" }
  }],
  "DEAL": [{
    "dealId": "series-b-follow-on",
    "stage": "diligence",
    "INVESTMENT_MEMO": [{ "memoId": "memo-northstar-q2", "status": "approved" }]
  }],
  "POLICY": [{ "policyId": "ic-approval", "requiresHumanReview": true }]
}

Working example

Ask a portfolio question. Return cited evidence or refuse.

The backend retrieves holdings and approved investment memos from RushDB, sends only cited evidence to the local vLLM endpoint, and requires record IDs in the response.

PORTFOLIO fo-2026
  HOLDING ai-infra-co allocation: 6.8%
  COMPANY "Northstar Compute"
  INVESTMENT_MEMO "GPU supply concentration remains the primary risk..."
  POLICY "Do not recommend trades without IC approval."
  DEAL "Series B follow-on diligence"

{
  "labels": ["INVESTMENT_MEMO"],
  "propertyName": "text",
  "query": "AI infrastructure exposure, concentration risk, and follow-up diligence",
  "where": {
    "PORTFOLIO": { "portfolioId": "fo-2026" },
    "status": "approved"
  },
  "limit": 8
}

{
  "answerability": "grounded",
  "summary": "AI infrastructure exposure is concentrated in Northstar Compute.",
  "citations": ["holding-ai-infra-co", "memo-northstar-q2", "policy-ic-approval"],
  "unsupportedClaims": [],
  "requiresHumanReview": true
}

TypeScript SDK

Retrieve evidence first. Run local inference second.

RushDB supplies schema, retrieval, relationships, and citations. vLLM runs the model inside the controlled environment. The thin UI only calls this backend workflow and is outside the blueprint scope.

from openai import OpenAI
from rushdb import RushDB

db = RushDB('RUSHDB_API_KEY')
llm = OpenAI(base_url='http://vllm.internal:8000/v1', api_key='local')

schema = db.ai.get_schema_markdown({
    'labels': ['PORTFOLIO', 'HOLDING', 'COMPANY', 'DEAL', 'INVESTMENT_MEMO', 'POLICY'],
}).data

holdings = db.records.find({
    'labels': ['HOLDING'],
    'where': {'PORTFOLIO': {'portfolioId': 'fo-2026'}},
    'limit': 50,
}).data

memos = db.ai.search({
    'labels': ['INVESTMENT_MEMO'],
    'propertyName': 'text',
    'query': 'AI infrastructure exposure, concentration risk, and follow-up diligence',
    'where': {'PORTFOLIO': {'portfolioId': 'fo-2026'}, 'status': 'approved'},
    'limit': 8,
}).data

answer = llm.chat.completions.create(
    model='local-wealth-model',
    messages=[{
        'role': 'user',
        'content': f'Use only this schema and evidence. Cite record IDs. Refuse unsupported claims.\n{schema}\n{holdings}\n{memos}',
    }],
)

Implementation blueprint

Build the on-prem wealth-intelligence path.

Use this sequence to build a private backend for portfolio intelligence without turning the model into the source of truth.

Relevant docs

Read the exact primitives behind this pattern.

These links point to the RushDB docs pages that map directly to this blueprint: ingestion, labels, properties, values, SearchQuery, relationships, semantic search, MCP, or deployment.

How it works

Build the smallest useful workflow first.

Know where it fits.

Questions developers ask.