The Human Web Is Becoming Agent Web
I'm joining Steel as founding growth lead. The web is shifting from human clicks to agent-run workflows. Steel aims to be the execution layer that makes agents reliable via traces + trust.
The Post-Copyright Era of Software
Copyright does not disappear in the AI era, but it stops functioning as a meaningful scarcity mechanism for software. As reimplementation gets cheap, the real moats shift to trust, governance, provenance, maintenance, and operational legitimacy.
Explore once, script forever: turning web runs into scripts
Give the agent a Steel CLI and SKILL.md contract, force a snapshot/click/fill loop, then turn the successful run into a rerunnable bash script.
The Hidden Language of Search
There's a hidden layer between human questions and search results. AI tools translate messy prompts into precise queries - and you can see the evidence in Google Search Console.
What Makes a Great Coding Agent
The best coding agents aren't about smarter models. They're about harness design: minimal core, extension hooks, radical transparency, real sandboxing, session forking, and headless RPC.
Designing CLI Tools for AI Agents
AI agents are now power users of your CLI tools. If you want them to succeed, you need structured output, deterministic exit codes, explicit sessions, and recovery primitives. Here's the complete checklist.
Eager Agents
LLMs are eager by nature. Give them an inch, they'll take 10 files. Here's how to scope agent work and prevent PR bloat.
From Bash Script to AI-Native Go CLI in One Session
A single AI session turned `scribe.sh` into `scriby`: a Go CLI with deterministic output, runtime bootstrap, and cross-platform releases.
40% of Signups This Week Came From AI Recommendations
Checked onboarding responses. Exactly 40% of new users in the last seven days found steel.dev through AI tools. Not Google. Not ads. Users told us this during signup.
Making CLIs Agent-Friendly with Loops and Schemas
A CLI for my web automation agent, built through structured loops: a todo-backed backlog, schema validation, and a verification harness running 50 random web actions per cycle. Agent reliability isn't philosophy—it's loops and logs.
Request an AI summary of this blog
