Engineering 2026-05-28
AI Agent Self-Violation Visibility — Cycle Design Beyond Memory
Why memory rules fail to stop repeat violations, and how a retro-gate-pipeline cycle creates structural AI self-improvement.
TAG
#System Design
7 articles
Engineering 2026-05-28
Pipeline Strategy Layer: Connecting Advisor Agents to Executor Skills
Wire advisor agents into pipeline phase 0 or they stay silent. Brief YAML as hub propagates SEO strategy to writing and review.
Engineering 2026-05-26
Representing Sister Pillar Relationships as First-Class Schema — A Brief Extension Proposal
Adding sister_pillar_slug to brief YAML separates sister pillars from spokes, aligning graph generation and cross-link skills.
Engineering 2026-05-26
Phase Design to Keep bateson Single-Tenant from Blocking Multi-Tenancy
Three Phase A rules prevent breaking changes at Phase B: tenantId in all API args, adapter DI, and cancelToken HMAC hashing.
Engineering 2026-05-25
Deploying Claude Code for Non-Engineers: CLAUDE.md and Permission Pitfalls
Practical guide for tech leads to design safe Claude Code environments via CLAUDE.md scoping, skill I/O, and permission models.
Engineering 2026-05-22
AI Agent Harness Design Principles — Ownership, Skill Delegation, and Fallback
Principles for designing a harness that safely delegates work to AI agents. Covers director agents, skill delegation, fallback phases, and deterministic skills in Claude Code.
Engineering 2026-05-21
Designing a Booking Engine from Scratch — From Contract Work to Commercial License
Full disclosure of the 4 abstraction rules that promote a contract-built codebase to a commercial license. Phase A→D stage design, adapter pattern, and tenantId allow SaaS prep to advance without breaking changes, while dogfooding continues.