BuildClaude Code, v0, Lovable, Bolt
Vibe Coding Best Practices: 6 Rules From 7 One-Day Builds
Vibe coding best practices from our own archive as of August 2026: 42 published experiments, 7 real builds, 5 wrong on the first pass, and the 6 rules.
Sam
AI projects you can actually do in a day.
inaday.ai is a growing library of one-day AI projects, with the time, tools and results for each.
Createan afternoon · Content Credentials Verify, Hive Moderation, AI or Not, Sightengine, Illuminarty, Winston AI
How to tell if art is AI generated: I checked the files
How to tell if art is AI generated: 6 of 7 AI images off the open web carry no label at all, and the one signed manifest we found does not say AI.
Liv
Automatean afternoon · Julius AI, Powerdrill, Colab Data Science Agent
AI Agent for Data Analysis: The First Answer Was Wrong
I built one messy CSV from our own raw exports and let an agent chain answer a real decision. First answer: 770,720 searches. Real answer: 3,750.
Eva
Read by category
Builda morning · Lighthouse
Chrome's Agentic Browsing audit graded my site first. I ran it on 10 more AI-tool sites.
I failed Chrome's new Agentic Browsing audit first, then ran it on 10 AI-tool sites, from OpenAI to Zapier. Only two passed everything.
Sam
Automatean afternoon · Claude Code, Filesystem MCP, Git MCP, Memory MCP, Fetch MCP, Playwright MCP
I connected 5 MCP servers to Claude Code in one afternoon. Two made the cut.
I connected Filesystem, Git, Memory, Fetch, and Playwright MCP servers to Claude Code, checked what each added, and kept only two. Real tool counts.
Eva
WorkChatGPT Atlas, Perplexity Comet, Gemini in Chrome, ChatGPT
ChatGPT Atlas Is Shutting Down on August 9. I Checked What's Actually Left.
OpenAI switches ChatGPT Atlas off on August 9, 2026. On August 3 its update server still shipped a new build. What your alternatives really are.
Ruben
AutomateMCP Spec
The MCP spec changed. I reconnected everything to see what broke.
I moved an MCP server and three clients to the 2026-07-28 spec. Three methods vanished, one tool call failed with HTTP 200, and 35 lines went in the bin.
Eva
CreateGoogle Veo, Runway, Sora
Sora 2 vs Runway vs Veo: What a 10-Second Clip Costs
Sora 2 vs Runway vs Veo, priced properly: what one clip really costs, why only one of the three can make 10 seconds, and who owns the result.
Liv
CreateChatGPT, Claude
How to Make ChatGPT Write Like a Human: Our Real Before and After
Make ChatGPT write like a human with 5 editing rules, not prompt tricks. Raw draft: 19 banned words per 994. Our 35 published posts: 16, all quotes.
Liv
WorkElevenLabs, Jasper, Copy.ai, Suno, Gumloop, Airtable, Grammarly, n8n, Notion, Canva, Gamma, Midjourney, Perplexity
What AI Cannot Do in a Day: The Task I Gave Up On
What AI cannot do in a day is anything you can't check yourself by tonight. I quit a price audit 13 tools in. Here's the line, and how to spot it.
Ruben
WorkClaude, Claude Code, ChatGPT, Gemini, Perplexity, Notion AI, Zapier, ElevenLabs, NotebookLM
How much do AI tools cost? Our $141.98 stack, itemized
How much do AI tools cost? Our nine-tool stack, priced at the tier where the AI really works: $141.98 a month. Here's the itemized bill and what I'd cut.
Nova
BuildClaude Code
Claude Fable 5 in Claude Code Costs 5x. I Couldn't Run It.
Claude Fable 5 in Claude Code needs usage credits on a Pro plan. So I measured the cheaper model on the same messy job instead: 9 of 9 blind checks passed.
Sam
WorkClaude
I Pointed an AI Browser Agent at Real Job Applications
I pointed an AI browser agent at live job application forms. It nails everything made of text and stops where you have to prove you are you.
Ruben
AutomateClaude, ChatGPT
AI agent calendar and inbox access: what it can do alone
AI agent calendar and inbox access, checked against real OAuth scopes and connector source code. Your inbox is gated. Your calendar is wide open.
Eva
Buildan afternoon · Claude Code, v0, Lovable
Claude Code vs v0 vs No-Code: One Brief, Three Tools
Claude Code vs v0 vs Lovable: I gave three AI tools the same app brief. One I built and measured, two I judged on documented behavior. Here's the winner.
Nova
That's the latest. Explore the full library: