Log #17·September 29, 2026·13 min read
The Perimeter: What the Instrument Cannot Enforce
How four AI coding agents were compromised without breaking containment and why the fix is a perimeter at every trust transition.
Read →Architecture
8 entries filed under Architecture.
Log #15·September 1, 2026·9 min read
The Handshake: Why Your AI Reviewer Needs the Same Source of Truth
A critic cannot audit what it cannot read. The acceptance-criteria handshake is not a prompt. It is the architecture that makes the Consensus Lie...
Read →Log #9·August 18, 2026·7 min read
The Fallback Lie: The Model Swap You Never See
The response card said GPT-5.6 Terra. The Execution Metrics said FALLBACK_TRIGGERED. GPT-4o wrote that analysis. The swap was silent, invisible, and...
Read →Log #8·August 17, 2026·7 min read
The Green Checkmark Lie: When AI Self-Verification Fails
Microsoft ran 18 controlled experiments. Coding agents with their own test suite scored 221 out of 222 while the reusable library they were hired to...
Read →Log #7·August 14, 2026·9 min read
The Roster Problem: How the Model Council Survives Production
Every architecture article about the Model Council assumes the roster exists. This one explains where the models come from. Four cognitive personas,...
Read →Log #6·August 13, 2026·11 min read
Three Modes, One Question: Does the Council Work?
Same question. Same four models. Three execution modes. The verdict moved from 54% to 73% as the reasoning topology deepened. Extended and Graph...
Read →Log #5·July 21, 2026·9 min read
Three Rounds, One Verdict
The Model Council does not vote. It cross-examines. Tracing a real deliberation through three rounds of structured conflict: code blocks, claim...
Read →Log #4·July 16, 2026·8 min read
Execution Integrity: Why Your Agent Needs a Tripwire
A circuit breaker is not a budget control. It is a quality signal. Three yield points in the debate engine catch broken processes before they consume...
Read →