D.I.Y. intelligence

Thinker. Tinkerer. Translator.

PruningMyPothos is a thinking workspace on AI systems, orchestration, platform integration, governance, and adoption.

What authority lives here

This site explores how modern AI systems actually work: LLM architecture, orchestration and agent workflows, retrieval and knowledge pipelines, governance and evaluation, and working experiments such as Soothsayer, runtime orchestration, and portfolio case studies.

How this workspace is organized

The work here is structured across four connected domains: systems, sentences, self, and shelf.

Suggested pathways

Start with systems thinking Architecture, orchestration, and reliability patterns. Explore language and meaning Short reflections on attention, meaning, and judgment. See experiments in practice Tooling and field notes from local AI workflows.

What this workspace helps you do in practice

This workspace helps practitioners design and operate AI systems with clearer language, stronger retrieval structure, and better decision traceability. It combines systems explainers, entity-level definitions, and handoff patterns so teams can ship faster with fewer silent failures across SEO, AEO, and GEO surfaces.

Featured from the Workspace

Hand-picked insights from across the collections

Systems Deep

Comparing Cloud Architecture in 2026: AWS vs Azure vs GCP

A five-layer architecture lens for choosing AWS, Azure, or GCP in the AI era.

systemscloudaws

11 min

Systems Deep

Embeddings Explained Like You're Human

Similarity over meaning, and why search works until it doesn't.

embeddingssearchmeaning

8 min

Systems Deep

I-7 Cognitive Loop: A new standard for Human-AI interaction

A governance-first interaction model that extends Norman's stages for AI-assisted work.

systemshciai

10 min

Systems Deep

Systems 001: Foundations

A technical field guide to systems as the infrastructure of evolution and communication, from boundaries and feedback to socio-technical layers.

systemsfoundationsfeedback

6 min

Self Deep

D.I.Y.

A quiet rebellion: fixing small things to build a steadier self.

diyphilosophyidentity

5 min

Self Deep

Attention Debt

What you borrow from your focus now gets repaid with anxiety later.

attentionidentitypractice

2 min

Self Deep

Designing My First Safety Constraint

What I learned designing the first architectural boundary in an autonomous system, and why I had to resist the urge to make it configurable.

autonomysafetyengineering

3 min

Self Deep

Learning to Say I Don't Know

What I learned about trust and reliability when I started designing systems that acknowledged the limits of their own reasoning.

uncertaintyreasoningtrust

3 min

Self Deep

What I Learned Debugging a Multi-Agent System

The debugging session that taught me why observability is not optional in orchestration, and what I now look for first when a multi-agent system misbehaves.

agentsorchestrationdebugging

3 min

Self Deep