Insights
Field notes from production
If it's here, it's because I used it, tested it, or watched it fail and wanted to write down why.
VideoWatch the videoClaude Code Agent View: One Screen for Every Background Session
Anthropic's new way to dispatch and manage many Claude Code sessions from one screen — what each row tells you and the shortcuts I use day-to-day.
claude-codeagent-viewbackground-sessions
ArticleRead more10 min readYour AI Team Doesn't Need More People — It Needs Agents
What 'supported by a fleet of agents' means in practice: which tasks automate, which don't, and where the ROI breaks down. Evidence from Stripe, Coinbase, Ramp, and Shopify.
production-aiai-engineeringteam-structure
VideoWatch the videoI Hit My Claude Code Limit and Tried Codex
After two weeks running Codex CLI as my daily driver, I didn't switch from Claude Code — I split. Here's how to share your setup across both tools.
claude-codecodexagents-md
ArticleRead more4 min readClaude Code Routines: Auto-Maintaining PR Evolution Numbers
A backend PR kept colliding with other merges on database evolution numbers. Four manual rebases later, I described the problem to Claude and let it write a routine to handle the rest.
claude-codeautomationai-development
VideoWatch the video14 min watchYour AI Assistant Doesn't Need a Bigger Model. It Needs Colleagues
The multi-agent supervisor pattern in Mastra: eight specialist agents on one local LLM, one supervisor, structural trust boundaries — using TypeScript.
agent-architecturemulti-agentmastra
ArticleRead more14 min readClaude Opus 4.7 + Claude Code: 7 Tips for the 1M Context Window
Practical tips for getting the most from Claude Opus 4.7's 1M context window in Claude Code. Effort levels, proactive compaction, subagent delegation, and session management from daily production use.
claude-codeclaude-opusai-coding-tools
VideoWatch the video20 min watchKarpathy's LLM Knowledge Base, Wired Into a Real Agent
How to build Karpathy's LLM knowledge base into a production AI agent using Claude Code plan mode, an Obsidian vault, and a local LLM.
claude-codeskillsplan-mode
ArticleRead more12 min readGoverning AI Agents Without Killing Them: What Actually Works in Production
Most AI agent governance advice targets boards, not builders. Three failure patterns, real TypeScript examples, and what a CTO should do Monday morning.
ai-agentsagent-architectureproduction-ai
VideoWatch the video22 min watchThe Quality Loop Your AI Agent Is Missing (Evals + Tracing)
Add an LLM-as-judge scorer to a Mastra agent, catch a fabricated action item your tests would never flag, and fix the prompt — no custom infra.
evalsobservabilityagent-quality
Nothing matches those filters.