Search
Posts
IntentCAD v0.12.0: The Approval Toggle That Wasn't
A rejected operation couldn't be toggled back to approved. Five commits and a patch release to fix the core approval state machine in IntentCAD.
Readj-rig Binary Eval Framework: Ten Epics, One Day
Building a full binary skill evaluation framework in a single day — ten epics from workspace scaffold to drift detection, with a calibration engine that measures whether your judges agree with themselves.
ReadIntentCAD Viewer — Closing the DWG FastView Gap
Web workers, animated zoom, progress feedback, and color-coded selections. The changes that took IntentCAD's browser viewer from prototype to production-grade — benchmarked against DWG FastView.
ReadDeep Dive Part 4: Z3 Formal Verification, the Three-Layer Stack, and Claude Code as Architect
How Z3 SMT solver replaces LLM-as-a-judge with mathematical proofs, the three-layer IRSB+Moat+Scout stack, and the story of Claude Code as the lead architect across 285 commits.
ReadDeep Dive Part 3: A 12-Package Nested Monorepo That Watches AI Agents for You
Inside the IRSB Watchtower: a 12-package pnpm monorepo with evidence verification, behavior signal derivation, risk scoring, and auto-dispute — ~500 tests of deterministic monitoring.
ReadDeep Dive Part 2: Cryptographic Receipts and the Evidence Pipeline That Proves What AI Agents Actually Did
How the IRSB Solver creates SHA-256 evidence bundles, signs them with Cloud KMS, and posts cryptographic receipts on-chain — creating an unforgeable audit trail for AI agent work.
ReadDeep Dive Part 1: Five On-Chain Enforcers That Make AI Agent Wallets Structurally Safe
How EIP-7702 delegation, five caveat enforcers, and bond staking create defense-in-depth guardrails for AI agent wallets — with 11 contracts live on Sepolia.
ReadDeep Dive Part 4: Building 10 Production Gems with Claude Code as Tech Lead
What it means when the AI makes the architectural decisions. How Claude Code served as tech lead across 10 Ruby gems with 2,924 tests and 60+ canonical docs.
ReadDeep Dive Part 3: The Observability Loop — Teaching AI Tools to Improve Themselves
How the wild ecosystem's three-repo pipeline — telemetry, transcript normalization, and gap mining — creates a feedback loop that teaches AI tools what they're struggling with.
ReadDeep Dive Part 2: CLAUDE.md — The Missing Manual for Human-AI Software Collaboration
How per-repo CLAUDE.md files act as binding contracts between human architects and AI implementers. The pattern that coordinated 10 Ruby gems across the wild ecosystem.
Read