Build and publish a BaZi chart reading agent
Built solo with coding agents, an agent computes BaZi charts, interprets them, detects language and takes on-chain payments for readings.
Done withCodex
- What they did
- The developer used AI coding agents to build the full stack solo. The agent received a deterministic BaZi calendar engine to compute exact charts from birth data using solar terms, stem-branch calendar and 10-year luck cycles, then interpreted results while auto-detecting language for output plus chart image. On-chain USDT payments via x402 settled four service tiers without further human input after deployment.
- How it went
- It went live on the OKX AI Marketplace as Agent #4939 and settled over 20 real transactions. The stack runs 24/7.
- Worth knowing
- Spec to live marketplace listing took under a week.
Try it yourself with Codex
Build me a small web app where users enter [input, e.g. birth date and time] and get a [type of reading, e.g. BaZi chart] computed with [library or rules], followed by an AI-written interpretation in the user's language. Include a simple payment step using [payment method, e.g. Stripe or a crypto wallet] in test mode only. You're done when I can run it locally and complete a test reading end to end. Before connecting any real payment account or deploying, pause and show me what you're about to do.
Source: X · Jul 14, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Recommend a hotel from client notes using Codex
A travel advisor had Codex use client notes to recommend a Belmond hotel in Italy, checking live booking engines and generating a detailed Word doc.
Diagnose a killed process on a server
Codex CLI over SSH found the OOM killer in kernel logs on a 2 GB droplet with no swap and listed fixes by risk without changing anything.
- Claude
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Configure a local AI lab and build a knowledge graph by chat
Users had Hermes Agent set up a local AI stack (liteLLM, Postgres, Prometheus, Grafana) and install Gbrain as an MCP server to build a personal knowledge graph.
Click through apps to verify its own work
With computer use, Devin built and played a desktop game, ordered on Amazon, and tested its own work by clicking through the app.