Meaning Architecture — Why Your Agents Fail on Context, Not Code
The gap between AI capability and AI deployment isn't technical. It's philosophical. Wittgenstein figured out the problem in 1953.
2026-04-28•11 min read
Agent harness design, context engineering, agentic infrastructure, and the emerging shape of agentic organizations. Practitioner-positioned, research-grounded.
The gap between AI capability and AI deployment isn't technical. It's philosophical. Wittgenstein figured out the problem in 1953.
The agent harness determines the behavior envelope, not the model. Six agent harness architectures — and why the sixth breaks what the others assume.
Implementation is free. Direction is scarce. The autoresearch paradigm applied to social infrastructure — who decides what's worth building?
The agentic operating manual is the missing governance layer between your org and its AI agents. Four layers that replace coordination overhead.
The consulting pyramid sustained McKinsey for a century. AI just collapsed the base. What replaces it isn't a leaner pyramid — it's a different shape.
Meaning Architecture — Why Your Agents Fail on Context, Not Code
2026-04-28•11 min read•essay
Permissionless Intelligence — The Autoresearch Democracy
2026-04-21•9 min read•analysis
Permissionless Intelligence — The Agent-Native Currency
2026-04-17•8 min read•analysis
The Thread Is the Unit — Knowledge Work After the Prompt
2026-04-14•9 min read•essay