Archive

Every published build and workflow that is not one of the current tools. The original interactive artifacts and writeups remain intact.

Builds

Filtered by #coding-agents. Clear filter

1 build

Interactive⚡ 1 evening

Claude vs Codex · judged by Gemini

What this proves

The coding-agent debate is usually abstract. Here are three real tasks, both agents run side by side, with a third agent judging the code excerpts and bugs. No cherry-picking, no vibes.

Three real coding tasks. Claude Code and Codex each run from the same task brief in a fresh sandbox. Gemini 3 Pro scores correctness, quality, speed, and fit. See the scored excerpts, the bugs, and the verdict.

ai-agentsbenchmarkcoding-agents

Workflows

13 workflows

10 minutes$0 (recipe runs on a bundled sample inbox)Beginner
Inbox → Action Queue (without touching real mail)
A take-home recipe that turns a bundled 50-thread sample inbox into a ranked action queue. Read-only pattern, human review required, zero credentials needed.
Built with Bundled sample inbox · Local extraction script · Markdown queue file
shipped on this site
60 words → this herogpt image 2 · 15 min
15 to 20 minutes$0 via ChatGPT PlusBeginner
Prompt-to-production landing page hero in under 20 minutes
The thumbnail on the Landing Page Critic build card is a GPT Image 2 output from my launch-day comparison, dropped into production in 15 minutes. Here's the 60-word prompt that got it, the export recipe, and why this replaces the 'hire a designer' step for a single-founder project.
Built with GPT Image 2 · ChatGPT Plus (Thinking mode) · sips (macOS) · Next.js · Vercel
live artifact
15 minutes$0Intermediate
Extract a Claude Design artifact into a live app component
Claude Design ships beautiful artifacts, but only as preview URLs. This workflow pulls the real HTML into your own app so you can embed it, theme it, and ship it, no Tailwind imitation, no screenshots pretending to be proof.
Built with Claude Code · Chrome DevTools MCP · Next.js · Chrome
20 minutes~$0.10 – $0.50Beginner
A/B test AI models on the same task before you commit
Same prompt, same inputs, two models. Surface the real differences on a task that matters to you, in 20 minutes, instead of picking based on someone else's benchmark.
1 of 4 shipped
real dataset
3 – 5 hours$0Intermediate
Turn a public dataset into a live explorer in one evening
Raw CSV or JSON from any open data source becomes a filterable, shareable explorer on your own domain. No backend, no API keys, no runtime cost. Proof lives on-site. I've run this four times.
Built with Next.js · CSV/JSON parsing · A chart library · Claude Code
2 hours initial setup + 15 min/day$0Intermediate
Karpathy's 4 principles for AI memory, implemented end-to-end
Karpathy's April 2026 post named the four constraints any serious personal AI memory system needs: Explicit, Yours, File over app, BYOAI. Here's each one translated into concrete implementation, with the pieces you actually install on day one.
10 minute read$0Beginner
The LLM-native memory pattern: a short field report
A short, dated history of how the 'personal markdown wiki for AI agents' pattern emerged, who shipped what, and why it all converged on the same four properties. Reading this first makes every other AI-memory recipe make more sense.

Archive

Builds

Claude vs Codex · judged by Gemini

Workflows

Inbox → Action Queue (without touching real mail)

Prompt-to-production landing page hero in under 20 minutes

Extract a Claude Design artifact into a live app component

A/B test AI models on the same task before you commit

Turn a public dataset into a live explorer in one evening

Karpathy's 4 principles for AI memory, implemented end-to-end

The LLM-native memory pattern: a short field report

Prompt → Visual Asset QA before anything ships

Research a physical product supply chain from one SKU

Demo GPT-5.5 with an inbound lead to proposal pack

QA your own feature with Chrome MCP before you ship it

Promote daily notes into agent knowledge that compounds

Run a personal LLM-native operating system (the Life OS stack)