AI & SYSTEMS

Beyond the answer.
Into the system.

An evolving exploration of how AI retrieves context, takes action, and fits into real software. The interesting part is understanding what happens between input and output.

EXPLORE SOMETHING TANGIBLE

See retrieval
take shape.

RAG Playground brings embeddings, retrieval, reranking, and evaluation into a visual, browser-based learning space.

Inside RAG Playground

CURRENT INTERESTS

Three questions worth following.

01

Context & retrieval

How does a system find the right information? Exploring RAG, knowledge graphs, and ways to make retrieval decisions visible.

GraphRAGEmbeddingsEvaluation
02

Agents & workflows

How do tools become a dependable workflow? An interest in orchestration, MCP, explicit boundaries, and human review.

OrchestrationMCPTool use
03

Local & connected

What belongs on the device, and what belongs in the cloud? Exploring local models alongside the infrastructure that makes systems useful.

Local modelsCloudArchitecture

RELATED NOTES

Keep following the thread.

All notes

Find a thread

Search across projects, notes, and ideas.