IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

11 articles

27 Jul 2026 · 8 min read

ai-agents

Why Software Factories Fail (and What Actually Works): A Tech Lead's Guide to the HumanLayer Series

Dex Horthy's two-part HumanLayer series lands on the same conclusion from opposite directions: 'lights-off' agentic factories that skip code review don't work, because RL training has no way to reward good architecture — only passing tests. The fix isn't less AI, it's front-loaded structure: research/plan/implement, frequent intentional compaction, and four review checkpoints before code gets written. Here's the synthesis and a rollout plan.

21 Apr 2026 · 9 min read

agentic engineering

Is Vibe Coding Dead? The Shift to Agentic Engineering in the AI Era

One year after Andrej Karpathy coined 'vibe coding', the industry is moving on. Discover why vibe coding fails at scale — context collapse, cognitive debt, zero system design — and how agentic engineering is emerging as the professional discipline for AI-first software development.

20 Apr 2026 · 25 min read

agentic-ai

The Harness Problem: Why Your AI Briefs Are Costing You More, Not Less

A personal take on the hidden cost of AI-generated briefs. When CEOs and managers skip the reasoning process and hand developers full AI implementations as 'briefs,' they double the workload instead of halving it. The same problem plagues multi-agent AI systems — and the solution is the same: a Harness.

20 Apr 2026 · 13 min read

Project Setup: BaseAgent, State, and Shared Infrastructure (Part 4 of 12)

Part 4 of 12 — Build the foundation: BaseAgent class, TeamState, agent config YAML, SQLite memory store, and tool registry.

19 Apr 2026 · 32 min read

agentic-ai

Building an AI Software Team: Why Simulate a Dev Team with Agents? (Part 1 of 12)

Part 1 of 12 — The vision behind building autonomous AI agents for every role in a software team: PO, BA, QC, TA, SSE, DevOps, TL, and PM. From solo developer bottleneck to an AI-powered development pipeline.

26 Mar 2026 · 6 min read

agentic

Agentic AI Developer Tools 2026: When AI Becomes Your Engineering Team

March 2026 marks a turning point — AI coding tools evolved from assistants to autonomous agents. As a Technical Lead, here's what you actually need to know to navigate JetBrains Central, GitHub Agent HQ, Dapr Agents, MCP, and the multi-agent revolution.

23 Mar 2026 · 7 min read

agents

Claude Opus 4.6 Agent Teams: Multi-Agent Development Is Here

Anthropic's Agent Teams feature in Claude Opus 4.6 lets multiple Claude Code instances work in parallel on the same codebase. Here's the architectural model, real-world performance data, and what actually changes for teams building production software.

22 Mar 2026 · 13 min read

AI-Driven Software Architecture: A Hands-On Guide for Engineering Teams (2026)

How AI is reshaping software architecture from the inside — ML-powered pattern selection, LLM orchestration, AI gateways, event-driven agents, and a full team implementation roadmap with diagrams and production-ready code.

20 Mar 2026 · 8 min read

agentic-ai

The Technical Lead in 2026: From Writing Code to Orchestrating AI Agents

94% of engineering leaders report agentic AI skills gaps. Here's what the tech lead role actually looks like in 2026 — and the skills you need to stay relevant.