“AI Agent” Search Is Up 23,000%. The Real Story Is Keyword Churn
Rising volume is the easy headline. Search intent is moving from build-an-agent tutorials to Gemini modes, Notion agents, Codex automation, and internal wikis.
Simple thoughts on building, designing, and shipping
Rising volume is the easy headline. Search intent is moving from build-an-agent tutorials to Gemini modes, Notion agents, Codex automation, and internal wikis.
When Fable 5 is available but capped, keep effort at high, reserve it for judgment, and push bulk work to Codex or Sonnet. Write the routing into CLAUDE.md first.
Gratitude note: opportunities compound only if work keeps shipping.
Push-to-talk on the menu bar with on-device SFSpeechRecognizer, optional LLM typo fixes only, and Bluetooth headsets that stay on A2DP. Requires macOS 26+.
appintoss-kit layers AGENTS.md, guides, skills, hooks, and review agents so Codex/Claude/Cursor stop missing policy, Korean UX, design rules, and store metadata.
A ChatGPT→Codex handoff bridge, multi-account config sharing via symlinks, a menu-bar status app, and an imagegen API with provider fallback.
I shared the deck and seven solo-builder workflows from the only solo-builder session I ran at Founder Day 2026 — including the fact Codex built the slides.
A full global skills library loads junk into every session. Keep one warehouse of clones and symlink only what each repo needs.
I did not chase follower count. The writing habit led here. Five notes on speed, planning, agent fleets, solo difficulty, and voice.
500M active parameters, R-SWA fixed-size KV cache, OmniDocBench beating much larger VLMs — multipage OCR without split-merge glue.
Every connection matters to me.
Feel free to reach out anytime.