Infrastructure

AI Lab

ClairVise private AI infrastructure for Finance & IB workflow

Architecture

AI Stack Overview

Input
Voice (Superwhisper)
Text / Documents
Reasoning
Claude
Open WebUI
Memory
AnythingLLM Vault
Knowledge Bases
Engine
Ollama
Apple Machine · Local
Automation
n8n
Fireflies
Hermes Agent
Philosophy

Design Principles

Local-first for sensitive data

Client documents, deal information, and proprietary models stay on-device. AnythingLLM and Ollama ensure no sensitive data leaves the machine.

Persistent knowledge graphs

Knowledge graphs maintain a structured memory of research, relationships, and concepts — enabling compounding intelligence over time rather than ephemeral chat.

Research-first AI

AI is deployed for deep research synthesis and first-pass analysis. Judgement, valuation conclusions, and client-facing outputs remain entirely human.