Model

Gemini (Default)

Example input

Sample Input Preview
[Role]: AI Solutions Architect & Fintech Strategy Consultant

[Technology]: Multi-Agent Orchestration and RAG (Retrieval-Augmented Generation)

[Industry]: Personal Wealth Management & Private Banking

[Current Process]: Manual quarterly portfolio reviews and client risk-profiling reports

[Projected AI Cost]: 85% reduction in analyst hours; scalable to 10,000+ clients at near-zero marginal cost

[Risk Variable]: SEC/FINRA compliance regarding automated financial advice and data residency

[Tone]: Visionary yet pragmatic

[Format]: Professional Executive Briefing with a Risk-Reward Matrix

[Audience]: Venture Capitalists and C-Suite Executives

[Priority]: Rapid market penetration and operational defensibility

Example output

Executive Briefing: The Future of Autonomous Wealth Management
To: Investment Committee & C-Suite Stakeholders

Subject: Strategic Implementation of Agentic RAG Frameworks

I. Strategic Technical Feasibility
The transition from static data silos to an Agentic Orchestration layer represents a fundamental shift in private banking. By deploying a Retrieval-Augmented Generation (RAG) architecture, we move beyond generic LLM responses to a system that queries live, proprietary market data and client history in real-time.

Infrastructure: Requires a robust vector database (e.g., Pinecone or Weaviate) to index private financial research and client portfolios.

Orchestration: Multi-agent frameworks (like LangGraph or CrewAI) will be deployed to assign specific "roles"—one agent for data retrieval, one for compliance checking, and one for narrative synthesis.