IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
27 articles
21 Jul 2026 · 6 min read
ai-agents
Single-agent coding assistants hit a context wall the moment a task spans more than one concern. Claude Code's answer is a Lead Agent coordinating Specialist Agents over a shared task system with hard context isolation — here's how the architecture works, and a concrete rollout plan for applying the same pattern to your team's workflows and your own projects.
Read more06 Jun 2026 · 7 min read
AI coding
Is your Claude Code token usage insanely high? The culprit might be your architecture. Learn how DRY principles and clear system design slash AI token costs.
Read more05 May 2026 · 6 min read
agentic engineering
Forget vibe coding. This is a real workflow: plan with agents, verify with QA, review as human, ship to production. Here is what it actually looks like in practice.
Read more05 May 2026 · 7 min read
agentic engineering
Every AI coding session that skips planning costs 3x more in debugging. Here is how plan mode works in Claude Code, real rejection logs, and why the QA agent rejects most first drafts.
Read more04 May 2026 · 12 min read
agentic coding
From vibe coding to software craftsmanship. 84% of developers use AI tools, but only 29% trust the output. Here is the maturity model that separates the amateurs from the engineers.
Read more20 Mar 2026 · 8 min read
ai-workflow
A practical guide to combining Google Stitch (free AI design tool) with Claude Code to create branded, production-ready websites — without the generic AI template look.
Read more19 Mar 2026 · 23 min read
ai-agent
A comprehensive guide to ClawTeam — the open-source Agent Swarm Intelligence framework. Learn how to set up Dev, QC, and Tech Lead agents on a single laptop, handle security and performance concerns, prevent AI quality issues, and run a solo complex project with production-grade workflows.
Read more19 Mar 2026 · 23 min read
ai-agents
A practical, hands-on guide to automating Developer, QC, and Tech Lead workflows across three maturity levels — Manual, Agentic (Claude Code), and Fully Autonomous (NanoClaw). With mermaid diagrams, real configs, BDD examples, and step-by-step instructions you can implement today.
Read more18 Mar 2026 · 13 min read
agentic-ai
Most people are stuck in Phase 1 of AI — asking questions and doing work themselves. Phase 2 is Agents: you set a goal, the agent delivers results. Here's the complete breakdown of what changed, how it works, and why it matters.
Read more
