Tute Costa

Front-load context on your first turn. Opus 4.7 stopped reading between the lines. 4.6 would interpret a vague prompt. 4.7 won't. Name the files. State the constraints. Define "done." Stop there.

Let's enable MFA for all Ruby gems thoughtbot.com/blog/lets-enab… Thank you @matheusrich for improving the Ruby ecosystem and community!

Find it here: github.com/tute/railspilo…. Take what's helpful, offer suggestions!

I just open sourced my AI toolkit, mostly for Ruby on Rails development:

thank you cursor 3 this morning i woke up to 5 PRs that i kicked off with cloud agents yesterday night. bugbot had reviewed all of them, suggested fixes, and auto pushed it while i was sleeping. then, another agent tested the changes to make sure they were functionally correct can also just spin up a bunch of agents on the same problem, see whicih one fixed it the best way i can never go back to not using cloud agents anymore, its changed the way i approach problems

Blog post by @fede_sapuppo about the journey: fedesapuppo.github.io/resume-website…

Fond memories of my college project reviving "old" desktops with Xubuntu. Configuring them without Claude was rough. And gotta love Omarchy, see blog post below.

[ENG] Now on stage! @matheusrich — "Production Data Doesn't Have to Be Scary" [PT-BR] No palco! @matheusrich — "Production Data Doesn't Have to Be Scary" #TropicalOnRails

[ENG] Day 1 of Tropical on Rails 2026 — the energy, the talks, the community, all in one video. [PT-BR] Dia 1 do Tropical on Rails 2026 — a energia, as talks, a comunidade, tudo num vídeo. #TropicalOnRails #RubyOnRails #SamedayEdit

Your AI agent ran without errors. The output looked reasonable. So you shipped it. That is not testing. New video: How to Know If Your AI Agent Actually Works youtu.be/Kleu3ROhpvY

Best piece I've read on building real software with AI. A full SQLite toolchain, with honest and objective breakdowns of where agents helped and where they made things worse. See within:

claude-code-workflows 2026.03.30 is out. What shipped: /doc-audit — audit codebase docs against actual code. Catches stale READMEs, outdated architecture docs, missing coverage. Auto-fixes small discrepancies, flags structural changes. Companion to agent-ready, because documentation rot is one of the fastest ways to degrade agent performance. /codebase-readiness — now scores PHP codebases. Ruby, Python, TypeScript, Go, Rust, and PHP all supported. /agent-ready — scaffolds domain knowledge documentation alongside AGENTS.md and ARCHITECTURE.md. Agents get context about your business domain, not just your code structure. Also documented the full release process. Calendar-based tags for the marketplace, semver per plugin. Two layers of versioning so plugins evolve at their own pace. Free, open source. github.com/dgalarza/claud…

Gumroad’s test suite of 16,000 tests has been flaky for years. This slowed down shipping tremendously. This week, Gianfranco used @karpathy’s autoresearch and @steipete’s OpenClaw to stabilize our test suite overnight. And his code is open source, so you can (have your agent) do it too. (And our code is open source too so you can see every single fix on GitHub.)

"It's a little creepy to be able to derive this much information about someone so easily, even when they've shared that freely in a public place. I use this to check that I'm not getting embroiled in an argument with someone who is [...] in bad faith." simonwillison.net/2026/Mar/21/pr…

Claude Code just went from a tool you sit in front of to something that reacts while you're away. Anthropic shipped Channels this week. Their answer to the demand that projects like OpenClaw proved. youtu.be/35J7IsT2K24

"How we cut a Rails test suite and CI time in half" evilmartians.com/chronicles/the… I just did similar things on a client's project (plus fixing caching bugs on Circle CI's config), with similar results.