Victor Velázquez

framesmith 2.1 and 2.2 are out: a commerce genre for checkout screens, a runnable test suite, a 45x faster viewer, and a pile of evaluator fixes.

I shipped a Ruby gem with parallel agents and a 37-agent review.

The thing agents are worst at is visual taste, so they fake it. framesmith 2.0 generates a full design language deterministically, no API key, AA by construction.

A design gate is only as good as its ability to notice reality drifted. framesmith 1.10 binds approvals to a content hash and turns drift into a CI check.

After running spec-driven development across several projects, the step that pays for the whole workflow is the one the docs mark optional: clarify.

Charts as a first-class node type, reusable components, bulk edits, and an evaluator that knows a dashboard isn't a landing page. framesmith 1.9.0 is out.

Orphaned subagents keep running and billing after their parent moves on.

framesmith 1.8 makes human design feedback structured — click any element, type a note, and the agent gets it anchored to the exact node it belongs to.

framesmith 1.7 adds a vetted pattern library and a machine-readable 'done' contract, so an agent crafts a good UI and won't hand you a half-finished one.

Loop engineering means designing the system that prompts your agent instead of doing it by hand — with a concrete RSpec loop you can run on a Rails app today.

Building framesmith v1.5's UI importer taught me the rule for any tool an agent consumes: be honest about your confidence, not just your output.

An agent disqualified a sales deal that should have been marked lost.

You just got onboarded to an 8-year-old Rails monolith.

Why I rebranded canvas-mcp three weeks after shipping it — and a 5-question naming checklist I now run on every OSS project.

Two engineers, same Claude Code, same task.

Anthropic's prompt caching silently does nothing if your cacheable prefix is too short.