GeezerVison

The World Wide Web, restored to 800 pixels of glory.

GeezerVison is showing flypython.com — Python challenge courses — solve with your agent — FlyPython

Start here

Your agent's tool course

Six free courses, one per coding agent. Lesson 1 is always the same three steps: get the tool running → install the FlyPython Skill (network on) → let the agent fetch the course.

Hands-on Python with Claude Code

A challenge course that takes you from a broken script to a tested, verified Python report tool — one sentence starts it in your agent, which fetches the course itself. Task contract, bounded change, and objective pass/fail evidence; guided agent-taught mode included.

Claude Code 2.x · Beginner · 5 challenges · Free →02

Hands-on with the OpenAI Codex App

The same verified Python workflow as the Claude Code course — task contract, bounded change, objective verify.py evidence — taught hands-on in the Codex desktop app: threads, approvals, AGENTS.md, and diff review.

OpenAI Codex desktop app · Beginner · 5 challenges · Free →03

Hands-on with Cursor

The same verified Python workflow as the flagship course — task contract, bounded change, objective verify.py evidence — taught hands-on in Cursor: Agent/Ask/Plan modes, .cursor/rules project rules, and accept/reject diff review.

Cursor (Agent mode) · Beginner · 5 challenges · Free →04

Hands-on with DeepSeek Harness

The same verified Python workflow as the flagship course — task contract, bounded change, objective verify.py evidence — taught hands-on in DeepSeek Harness: plugin-composed agents and an auditable append-only trajectory.

DeepSeek Harness · Beginner · 5 challenges · Free →05

Hands-on with Kimi Code

The same verified Python workflow as the flagship course — task contract, bounded change, objective verify.py evidence — taught hands-on in Kimi Code: built-in explore/plan/coder subagents keep reading, planning, and editing in separate lanes.

Kimi Code CLI · Beginner · 5 challenges · Free →06

Hands-on with ZCode

The same verified Python workflow as the flagship course — task contract, bounded change, objective verify.py evidence — taught hands-on in the ZCode desktop workspace: Goal Mode task decomposition and the Git state as your review surface.

ZCode desktop app · Beginner · 5 challenges · Free →07

Hands-on with GitHub CopilotNew

The verified Python workflow — task contract, bounded change, objective verify.py evidence — taught hands-on with GitHub Copilot in VS Code, where the Agent role runs the loop and you supervise permissions, instructions files, and diffs.

GitHub Copilot in VS Code · Beginner · 5 challenges · Free →

Skill-driven

Every course is one sentence away

Paste the entry sentence from a course page; your agent handles files, verification, and submission. Read the challenges online first — no account needed.

Difficulty: Beginner — first agent or first Python project; Intermediate — comfortable running an agent and reading code; Advanced — multi-step builds with real verification.

One source of truth for agent rules

Stop maintaining diverging AGENTS.md, CLAUDE.md, and .cursorrules files — build a checker that proves your repository has exactly one rule source.

Intermediate · 5 challenges · 1–2 hours · Free →02

From “it runs” to “it ships”: verifying AI-generated code

Build the release-evidence machine your AI-written project is missing — a ship check that parses what actually ran, refuses zero-test projects, and writes an honest delivery record.

Intermediate · 5 challenges · 1–2 hours · Free →03

Give your agent tools with MCP (Python)

Build a stateless Model Context Protocol tool server in pure Python — JSON-RPC 2.0 dispatch, schema validation, error isolation, and the 2026-07-28 input_required round-trip.

Advanced · 5 challenges · 2–3 hours · Free →04

Build LLM features in Python: structured output, tool calls, and evalsNew

Turn a demo-day model call into a feature you can ship — validate structured output, allowlist tool calls, retry with the error fed back, fall back to a human instead of guessing, and measure it with an offline eval that divides by every case.

Intermediate · 5 challenges · 2–4 hours · Free →05

Security review for AI-written PythonNew

Review a plausible, AI-style notes service the way an attacker would — close SQL injection, path traversal, a hard-coded secret, fast password hashes, and pickled sessions one class at a time, then prove each fix by replaying the attacks.

Intermediate · 5 challenges · 2–4 hours · Free →06

Exploratory Data Analysis with an Agent

A challenge course — point your agent at a messy shop export and produce a verified EDA summary whose numbers are checked against ground truth.

Beginner · 5 challenges · 1–2 hours · Free →07

Data Visualization with an Agent

A challenge course — turn a clean sales dataset into three spec'd charts plus a summary.json whose numbers are verified against the data.

Intermediate · 5 challenges · 1–2 hours · Free →08

From Analysis to Report with an Agent

A challenge course — turn a verified EDA summary into report.json + report.md where every number traces back to its input unchanged.

Intermediate · 5 challenges · 1–2 hours · Free →09

pytest in the Loop — Tests That Catch Bugs Pro

A challenge course — given a correct library and a seeded buggy variant, write a pytest suite (fixtures, parametrize, raises) that passes on the reference and fails on the bugs. A suite that cannot catch a bug is not a suite.

Intermediate · 5 challenges · 1–2 hours · Pro →10

Package and Ship a CLI Pro

A challenge course — turn a Markdown-indexer script into an installable package: pyproject metadata, console entry point, built wheel and sdist verified by the contract suite — including a real install into a fresh virtualenv.

Intermediate · 5 challenges · 1–2 hours · Pro →11

A Verified Web API Pro

A challenge course — a FastAPI snippets service violates its own spec in six places. Fix the app until the provided contract suite is green, then write the tests for what the spec leaves unpinned and prove they catch planted regressions.

Intermediate · 5 challenges · 2–3 hours · Pro →

How it works

One sentence. One command. One honest verdict.

1. Authorize. Your agent shows you a one-time link and a short code; you compare and approve. No passwords, no downloads.

2. Solve. The agent fetches the course folder and works the TASK.md contract with you. Want a guide? COURSE.md runs an optional agent-taught mode.

3. Check and confirm. python verify.py runs your starter tests and prints checkpoint status. Complete each lesson's reflection questions, then explicitly confirm its self-reported checkpoint with --attest ID.

Inspect the repository ↗Editorial standards →

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.