Fetching from the wire…
Public story · 2026-07-15 · high
The practical shift for builders: spend less time on prompt wording, more on skill files and stopping conditions.
Why now: swyx's synthesis lands the same week as Mollick's July 14 Forbes piece and SkillOpt's top HuggingFace trending spot, three signals pointing one direction.
The discipline shifted from building agents to building harnesses around them, per a Latent Space synthesis of AI Engineer World's Fair 2026. For builders, that reframes what's worth learning: prompt tricks are becoming junior-level skills, while designing verification steps and stopping conditions is the senior work now.
Lilian Weng, now at Thinking Machines Lab, called her whole practice harness engineering. Anthropic's Thariq Shihipar said models are grown, not designed. Addy Osmani named the human outer loop the real engineering surface, per the same recap.
Other trends from the Fair point the same way. Forward Deployed Engineers are showing up inside Sierra, Cursor, and Warp. Coding agents like Claude Code, Codex, and Gemini CLI are replacing IDEs outright. Philipp Schmid called it skills as files: markdown documents that extend what an agent can do.
It's not one writer's take. Ethan Mollick's Forbes piece argues prompt-craft is junior work now. The senior skill is managing agents: giving them goals, output definitions, and tests, then supervising. Kent C. Dodds said flatly that prompting is for juniors, and that architecture now belongs in the prompt. Anthropic's Boris Cherny pushes the same idea under harness engineering: design the loop, not the wording.
SkillOpt, a paper on self-improving agent skills, sits atop HuggingFace's trending list with 256 upvotes.
I've seen this in my own projects. The wins lately didn't come from sharper prompts. They came from better verification steps and clearer stopping conditions.
Watch whether teams start versioning their agent skills as diffable markdown files instead of burying instructions in chat threads. That's the tell for who's actually building the harness and who's still just prompting.
Each link below shares sources, entities, or timing with this story.
Boris Cherny works at Anthropic / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Boris Cherny works at Anthropic); both cover Anthropic, Claude Code, Codex, Cursor; reported by the same outlet (huggingface.co).
Boris Cherny uses Claude Code / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Boris Cherny uses Claude Code); both cover Build, Claude Code, Codex, Cursor; reported by the same outlet (latent.space).
Boris Cherny works at Anthropic / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Boris Cherny works at Anthropic); both cover Addy Osmani, Anthropic, Claude Code, Cursor; overlapping topics (agent, engineer, loop, skill).
Boris Cherny uses Claude Code / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (Boris Cherny uses Claude Code); both cover Claude Code, Codex, Cursor, Gemini CLI; earlier Claude Code coverage from 2026-05-14.
Boris Cherny uses Claude Code / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Boris Cherny uses Claude Code); both cover Claude Code, Cursor, Latent Space, Spend; reported by the same outlet (latent.space).
Boris Cherny works at Anthropic / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Boris Cherny works at Anthropic); both cover Anthropic, Build, Claude Code, Cursor; overlapping topics (agent, anthropic, around).
Linked by a graph relationship (Boris Cherny works at Anthropic); both cover Anthropic, Claude Code, Codex, Cursor; overlapping topics (agent, markdown, skill).
Boris Cherny uses Claude Code / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Boris Cherny uses Claude Code); both cover Claude Code, Codex, Cursor, Gemini CLI; overlapping topics (agent, skill).