Executive intelligence
Live (Private)Personal Executive Intelligence Layer
Personal intelligence layer — executive knowledge, opportunity tracking, and personal decision support.
Overview
Personal executive intelligence layer — a customisable intelligence companion rather than a generic AI assistant.
Problem
Programme and transformation work generates scattered notes, architecture documents and conference material — querying that context quickly matters, especially when external AI services are not an option.
Why I built it
I wanted a completely customisable intelligence layer that helps me stay informed about opportunities, developments, projects and long-term knowledge without relying on external AI services.
Who benefits
Myself — as a programme lead with many notes, architecture documents, and conference materials I want to query quickly without uploading them to the cloud.
Current status
Live (Private) — personal intelligence layer for opportunities, knowledge, and decision support.
Architecture
Current implementation — based on what is built today.
Technology stack
TypeScript · Electron · Local LLM · Vector DB · RAG
Lessons learned
- Local AI is feasible, but setup and model choice are product decisions
- RAG quality depends more on ingestion than on the model
- Personal use is the best test for operations problems
Future direction
- Refine chunking strategies (PDF vs. Markdown)
- Evaluate MCP tool layer — explicit tool contracts for local actions
- Observability for RAG pipeline: which chunks, which model, which latency