Vibe Coding

Jason Zook shares a two-model software development workflow using Claude Opus 4.7 for planning and building, GPT-5.5 for adversarial review, and Playwright for automated UX/UI testing. The loop runs plan→review→update→build→review→fix→deploy, with ~$400/month replacing what feels like a full dev team.

JustHireMe is an open-source, AGPL-licensed desktop app (Tauri + React + Python/FastAPI) that addresses broken job search UX with a local-first, explainable AI pipeline: scrape → quality gate → rank → match (GraphRAG + vector) → generate tailored application materials. All data stays on-device by default, LLM usage is keyless-capable via Ollama/Claude Code CLI, and the architecture prioritizes human-in-the-loop control over blind automation.

Google's open-source Design.md format captures typography, colors, and spacing in a single markdown file that agents reference to produce consistent outputs. Combined with reusable skill files (landing page, mobile, pitch deck), it creates a design system any AI agent can apply uniformly across all surfaces—replacing the common pattern of polishing one screen while everything else looks generic.

Ben Tossell cancelled Superhuman and built a custom email client using Codex. It mirrors Superhuman's UX patterns but is fully customisable, runs on Gmail CLI, and is agent-native. The core AI logic is minimal: reading labels/archives and updating Gmail filters.

Tobi Lütke describes River, Shopify's internal AI coding agent living in Slack, designed with one hard constraint: it only works in public channels, not DMs. This forces all AI-assisted work into the open, creating a 'Lehrwerkstatt' (teaching workshop) where knowledge spreads osmotically. In 30 days, 5,938 employees used River across 4,450 channels; it opened 1,870 PRs in one week (~1 in 8 merged PRs). Merge rate climbed from 36% to 77% over two months purely from collective human feedback, not model changes.

A structured /goal prompt template for AI coding agents (Codex, Claude Code, Hermes) that prevents scope creep, ranks uncertainties before acting, and closes completion loops. Key sections: GOAL (single measurable outcome), CONSTRAINTS, PLAN (understand-first), DONE WHEN (verifiable state), VERIFY (tests + rollback), STOP RULES (halt on ambiguity, surface ranked proposals not open questions).

Claude Code's /goal and Codex's /goal commands implement a completion-contract pattern: a working agent loops until a separate evaluator confirms a stated condition is met, judged only from evidence surfaced in the conversation. The post argues this punishes vague PM requirements faster than traditional development, raising the bar from 'write enough detail an engineer understands' to 'define done clearly enough an agent can keep trying and a harness can inspect proof.' Includes a practical goal template and anti-patterns.

Nick Baumann describes a multi-device Codex setup where a Mac mini serves as an always-connected 'home' node and a MacBook becomes a 'satellite,' with mutual SSH and cross-device thread continuity giving him phone-initiated, 24/7 Codex access across all three devices.

Michael Guo notes that Chrome Browser and Hyperframe are both available as Codex plugins, making them straightforward to incorporate into AI creative workflows.

Claude Code's real power comes from building the ecosystem around it—persistent memory (CLAUDE.md), project initialization (/init), parallel Git worktrees, MCP servers, plugins, subagents, and CI/CD integration—rather than prompting better. The claude-code-setup plugin automates recommending and installing these components.