Field Notes

Matt Dailey (Ref) outlines a 7-step design process for AI-assisted product design: fixing constraints before jumping to solutions, removing AI-added bloat, iterating in dedicated design tools rather than the live codebase, using component libraries, leveraging preview deploys, stealing proven UX patterns, and deliberately building personal taste.

A GTM automation architecture organizes 19 APIs into seven sequential layers (Signal, Data, Action, Automation, Record, Conversion, Revenue), with ColdIQ acting as a unified router behind 10 of the 19 keys, letting Claude Code operate as the orchestrating agent from first signal to closed revenue.

Anthropic's Claude Code team formally defines agentic 'loops' as cycles of work repeated until a stop condition is met, categorizing them into four types (turn-based, goal-based, time-based, proactive) by what gets handed off. Charlie Hills synthesizes the framework with practical commands (/goal, /loop, /schedule, skills) and a warning that every loop still needs an explicit stop condition or it burns tokens unattended.

A SpaceXAI engineer's tutorial on Grok Bot, a desktop app giving each agent its own cloud computer to log into tools, execute multi-tool workflows, and coordinate with other agents—shifting the user from prompting to delegating and managing approval boundaries.

Ian Vanagas distinguishes 'writing with AI' (using AI for research, gap-finding, and fact-checking while keeping prose fully human) from 'using AI to write' (having it draft prose). He details a research skill stack for sourcing real examples, explains why AI is weak at summarization and editing/conciseness, and links this to a broader thesis on why AI hasn't produced 10x more 'banger' blog posts the way it has for code.