Writing Agentic Coding Weekly. Previously ML Engineer at Mercari.
Workflow
Jun 18, 2026
•
3 min read
Use local speech-to-text with Pi coding agent to turn spoken requests into shell commands and answers in your terminal.
Weekly
Jun 15, 2026
2 min read
Also: Kimi K2.7 Code, GLM-5.2, MiMo V2.5 Pro UltraSpeed, and MiMo code.
Jun 9, 2026
Also: Qwen 3.7 Plus, usage-based GitHub Copilot billing, Open Code Review, and and a TDD skill worth bookmarking.
Monthly
Jun 3, 2026
16 min read
Everything important in agentic coding this month, distilled for engineers and technical leaders.
May 25, 2026
Also: Antigravity CLI, Qwen 3.7 Max, DeepSeek V4 Pro's permanent discount, and aliases to stay sane across coding agents.
May 18, 2026
Also: Claude plan changes including +50% weekly limits, Grok Build CLI, and why you might want worse models on purpose.
Cheat Sheet
May 13, 2026
8 min read
A concise OpenCode CLI reference for agents, MCP, skills, config, workflows, and commands.
May 12, 2026
13 min read
A concise Claude Code CLI reference for commands, flags, MCP, skills, agents, hooks, and workflows.
May 11, 2026
Also: Simon Willison on the guilt of not reviewing AI code, running DeepSeek V4 Flash locally on Apple Silicon, and HTML for agents.
May 9, 2026
A concise Codex CLI reference for commands, flags, MCP, skills, subagents, config, and workflows.
Apr 27, 2026
4 min read
Also: Zed parallel agents, Claude Code postmortem, Copilot plan changes, and Roo Code shutdown.
Mar 23, 2026
7 min read
Also: A practical multi-agent workflow and three reads on specs, codegen, and real-world usage.
Deep Dive
Mar 20, 2026
9 min read
Are you still typing every prompt? Use voice typing with Claude Code, Codex, Cursor, Copilot, or any coding agent to give richer context with less effort.
Mar 18, 2026
5 min read
Also: Gemini CLI plan mode, JetBrains Air, `/btw` and voice mode in Claude Code, and 8 levels of agentic engineering.
Mar 9, 2026
6 min read
Also: Gemini 3.1 Flash-Lite, voice mode in Claude Code, agentic engineering patterns, and the debate over AI-assisted relicensing.
Mar 2, 2026
Also: RTK CLI proxy to minimize LLM token consumption, two new skills in Claude Code, and voice dictation in Codex CLI.
Quiz
Feb 25, 2026
Test your knowledge of Claude Code's subagent system and custom subagent configuration.
Feb 23, 2026
17 min read
Also: Taalas's LLM ASIC chip, building side projects with AI, and Claude Code subagents quiz.
Feb 19, 2026
Five questions on Claude Code's memory system: hierarchy, rules scoping, imports, and --add-dir.
Feb 16, 2026
Also: Karpathy's 243-line GPT, optimizing agent harnesses, and a quiz on managing Claude Code memory.
Feb 11, 2026
SWE-bench Verified is the most most commonly reported coding benchmark. Test your understanding with 5 quick questions.
Feb 9, 2026
12 min read
Also: Qwen3-Coder-Next for local dev, Codex app for macOS, and building a C compiler with 16 parallel Claudes.
Feb 4, 2026
Test your knowledge of the Agent Skills specification with five questions on structure and usage.
Feb 2, 2026
Also: Karpathy's notes on agentic coding, notes from Claude Code team, and Anthropic's study on impact of AI assistance on coding skills.
Jan 26, 2026
Also: How to fix generic AI UI using Anthropic's frontend design skill, Gas Town patterns, Claude Code best practices, and Codex agent loop.
