---
title: "First personal dinner-planning app"
canonical: "https://agenticfeats.com/c/first-personal-dinner-planning-app-codex/"
agents: ["Codex"]
evidence_grade: "A"
outcome: "completed"
job_type: "Personal and Family"
roles: ["Personal"]
source_url: "https://beginningwithi.com/2026/03/03/retirement-hobby-built-my-first-app-in-under-a-week"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# First personal dinner-planning app

A non-programmer used Codex to build a local web app that suggests dinners from pantry, garden, dietary rules, appliances and weather.

Result: Built a working What's for Dinner app with pantry, garden, recipe and restaurant pages plus a suggestions engine, in under a week.

## How it was set up

Codex working in a local project folder. ChatGPT drafted the starting prompt. Stack: Python, FastAPI, SQLite, uvicorn, Jinja2. Runs in a browser on the author's Mac.

## Worth knowing

Personal use only, runs on one laptop. The author had to approve Codex's terminal and file operations on macOS.

## Prompt

```text
You are a careful senior engineer building for a non-coder. Project: [app name], a local macOS app, no cloud. Use [backend], SQLite, and simple HTML. Build in small milestones, and after each say how to run it. Milestone 1: CRUD screens for [list of data types]. Write a README with run steps.
```

## Evidence note

Blog post with screenshots and a detailed build description; no public repo

## Sources

- Original: https://beginningwithi.com/2026/03/03/retirement-hobby-built-my-first-app-in-under-a-week

## The receipt

- Agent: Codex
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Personal and Family
- Roles: Personal
- Source: Blog
- Added: 2026-10-13