Seroter's reading list: AI coding workflows, subagent tradeoffs, and AI's zero financial payoff
rseroter · x · 2026-10-27
Richard Seroter's daily reading list (#896), heavy on AI workflows and enterprise AI value:
AI coding & agents
- "My AI Coding Workflow, v3" argues skills should encode workflow/process preferences, not product usage the harness already handles.
- An Anthropic post makes a solid case for when to fold subagents into your main agent loop.
- "Your AI Agent Doesn't Need to Keep Every File It Reads" — smart context management thinking.
- Don't ask AI to write your user stories; stop building apps only for humans — move logic out of UIs agents won't use.
Business value
- An Apollo economist says AI delivers 'zero financial payoff' to most companies — margins and revenue per employee stay flat because few firms make structural changes; a companion piece offers 3 paths to shareholder returns with AI.
Also: self-learning context enrichment in Knowledge Catalog; native Markdown lifecycle in Google Docs/Drive ("10/10"); how Google Beam connects military families.
More from coding & agent
- Cursor's new Agent SDK copies eve.dev conventions, signaling an emerging standard for agentic development — cramforce · 2026-10-27
- davidfowl claps back at theo: too many hand-merged PRs means you work with people, not agents — rakyll · 2026-10-27
- QuixiAI Open-Sources QuixiDesk, a Claude Desktop Clone That Runs Any Model — QuixiAI · 2026-10-27
- "Living on-call with Codex and Claude": devs joke their agents pager them 24/7 — sloppenheimer · 2026-10-27
- Power user plans full trip with AI agents: great at rebooking, terrible at audit trails — manosaie · 2026-10-27
- Dev builds an agent escape room: Beam solves puzzles by writing Python in CoreWeave Sandbox — wandb · 2026-10-27