<!-- Generated from the same source as https://ntinno.net/ai/ -->

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 ](/work/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 ](/notes/)

AI & systems · Working note

### [Make retrieval visible before making it clever](/notes/making-retrieval-visible/)

A working checklist for looking beyond the final answer and inspecting the context that produced it.

3 min read

App development · Working note

### [Privacy starts at the architecture sketch](/notes/privacy-as-a-design-constraint/)

Work out what needs to leave the device before deciding what the interface should promise.

3 min read
