AIMM Knowledge Hub
Essays, mastermind recaps, intelligence briefings, and prompts on building durable practice in the age of AI.
Recent articles
All articles →standalone
The Scoreboard Is the Moat
How to turn your own taste into a number, gate your publishing on that number, and grow a set of checks that gets stronger every week — no engineering required.
standalone
Every Decision Was a Decision to Build Less
A meta-analysis of the reasoning pattern that ran through one refactor session — and how to turn it into a thinking skill you can run on purpose.
standalone
I Stopped Trying to Prompt My Way Out of AI Slop. I Built a Scoreboard Instead.
A working session where an X post about fixing AI slop became a real, running quality gate — one that blocked a bad change, caught a silent production dip, and turned every failure into a permanent test.
Latest briefings
All briefings →Briefing #5
Weekly Intelligence Briefing: May 31–June 6, 2026
Content quality scoring became shared infrastructure with a six-genre rubric layer, the framework got its final name (Ambient Intelligence Architecture), and the herenow site crossed from a flat archive into a navigable knowledge interface.
Briefing #4
Weekly Intelligence Briefing: May 21–28, 2026
The Ambient Intelligence Framework acquired a security model with v0.4, the AIA resource inheritance system solved Claude's skill-library problem with a manifest/lockfile pattern, and Council deliberation ran as a scheduled task for the first time.
Briefing #3
Weekly Intelligence Briefing: May 14–21, 2026
Modal subtraction emerged as a codified architecture for original thinking, the GIC LEAP app pivoted from a hosted web stack to a Claude-native skill in days, and the LKB-Vault crossed a scale threshold requiring human-in-the-loop triage.
Mastermind recaps
All recaps →Recap · AIMM
Ambient Intelligence Culmination
Months of scattered pieces—context management, token use, model optimization, skill sharing—snap together this week into one unified architecture for carrying intelligence through the environment.
Recap · AIMM Spring 2026
Pay Once for the Reasoning
Months of scattered pieces — context management, token cost, model routing, skill sharing — snapped together in one session. Lou walked through the architecture live.
Recap · AIMM
Output Quality Gate
Stop fixing the input. The model is not deterministic. Build an external evaluation agent with a gold-standard rubric that any skill can call before publishing.
From the prompt library
All prompts →thinking
Tree-of-Thought Prep — Adversarial Exploration Before the PRD
Think in a Tree Before You Write the PRD
claude-sonnet-4-6
meta
PRD — Capability-Architect
Ambient-intelligence walkthrough — capability-architect as compiler
claude-sonnet-4-6
meta
Cheap-Model Prompt
Cost Optimization / Systems — use the smartest model to prompt the cheapest model
claude-sonnet-4-6