10 Tools · 5 Topics

AI Tools

My attempts to learn by building so I can offer sensible suggestions at work. I think of my stack in five layers: memory & knowledge, LLM agents, and business tooling.

01 · Foundations

Memory & Knowledge

My AI agents should know my work better than I do. When I start an Agent session, the conversation should load all historical and current context, preferences, conventions, and templates for the featured and related projects.

02 · Control Plane & Canvases

Vendor-Agnostic Tooling

Seamlessly swap between all LLM vendors, models, and CLI clients without needing to configure tools, manage authentication, or security.

03 · Voice & Feel

Grammar for Everything

One token system and visual grammar (Imagism) across R/ggplot2 charts, analytical briefs, slide decks, and web UI, paired with a 97-term part lexicon for surgical edits.

04 · Multi-Agent Pipelines

Operationalizing AI for Research & Analysis

Automating K-12 survey research, psychometric analysis, and publication-ready district impact reports through stage-gated multi-agent pipelines where every number in the prose is verified against source tables.

05 · Applied Learning Design

What are my CLI agents doing?

Ultimate goal: turn work into a video game where I instruct NPCs to do my job.