Building on Rented Intelligence: The Receipts Behind Claude's Silent DowngradeSep 21, 2026·3 min read
Part 4: Real-Time Pipeline DiagnosticsCalibrated Flake vs. Regression Triage in Automated Builds Sep 23, 2026·5 min read
Part 1: The Missing Primitive in Agentic AI — Kicking the Tires on TypeSafe's JevSep 18, 2026·7 min read
Resolving a Council of Independent AI Reviewers into a Single DecisionRunning multiple frontier LLMs in parallel to evaluate prompt pipelines, codebases, or architectures is straightforward. The hard part is reconciling their outputs. When three independent agents—such Sep 18, 2026·7 min read
Council Calibration: How Four Agent CLIs Handled a Bounded Research TaskThis is another short, practical, technical memo. As I dig more deeply into Herdr for multi-agent orchestration, I encounter concepts I think that might be useful for others to see. In this case, I waSep 17, 2026·8 min read
Operational Notes: Orchestrating Multi-Agent CLI Councils Inside HerdrTerminal multiplexing frameworks like Herdr bridge coordinating agents and autonomous worker CLIs (such as Codex, Grok, and Anti-Gravity). This allows you to spin up multiple agents from different proSep 16, 2026·7 min read
Incident recap: a fully specified planning task, and how Claude Code still got it wrongThis is an incident recap that shows why I still have no trust in Anthropic's latest models, even Fable 5.1 -- even when you follow their prompting guidance. Here's a quick background. I was working oSep 14, 2026·9 min read
The Information Ladder in the AI SDLCLast week, Anthropic published The AI-Native SDLC playbook, outlining how committed markdown artifacts—intent.md, spec.md, and plan.md—replace the slow, manual handoffs of traditional engineering. It Aug 27, 2026·9 min read