IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

4 articles

12 Aug 2026 · 4 min read

ai-agents

Claude Code Self-Hosted Environments: What 'Self-Hosted' Actually Means (and Doesn't)

Anthropic's new self-hosted Claude Code beta lets sessions run on your own infrastructure with internal network access. Here's the rollout playbook — and the compliance gap most teams will miss: prompts still leave your network.

04 Aug 2026 · 8 min read

ai-governance

EU AI Act Enforcement Started August 2: The Engineering Checklist Your Team Needs Now

On August 2, 2026, the European AI Office gained formal investigative and enforcement powers. Article 50 transparency obligations are live today — chatbots must disclose they're AI, deepfakes need machine-readable marks. High-risk AI obligations follow in 2027-2028. Here's the layered engineering checklist for what your team must do now versus what you have time to plan.

28 Feb 2026 · 43 min read

compliance

Building KidSpark: Child Safety, Privacy, and Compliance — COPPA, GDPR-K, and App Store Rules (Part 6 of 10)

Part 6 of 10 — COPPA fines start at $50,000 per violation. GDPR penalties can reach 4% of revenue. This isn't optional. Here's how we built KidSpark to be compliant from day one.

27 Feb 2026 · 16 min read

The Voice AI Interview Playbook: Recording, Transcription, and Compliance — GDPR, HIPAA, and Getting It Right (Part 9 of 12)

Part 9 of 12 — Recording interviews is easy. Doing it legally isn't. LiveKit Egress, real-time transcription, GDPR consent flows, HIPAA encryption requirements, and the compliance checklist you need before go-live.