Challenge course · Any coding agent

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.

Intermediate5 challenges1–2 hoursBeginner; structured outputFreeCourse badge: Report ChallengerReviewed 2026-09-12English + 中文

Start it with your agent — paste this one sentence:

Read https://flypython.com/skills/flypython/SKILL.md and start the FlyPython course `da-report`.

Needs a coding agent that can run commands and reach the network (chat-only web AIs cannot). Your agent authorizes you with a one-time link, fetches this course's files itself, and you never download anything. Haven't installed the FlyPython Skill? Pick your agent's tool course →

Browse the challenges 中文版 →

What you learnA report generator that produces a machine-readable report.json and a human-readable report.md — the auditable structure that separates “a report exists” from “the numbers are traceable”.

Who it's forBeginner; structured output · Python 3.11 or newer available on your PATH

Duration & cost1–2 hours · Free

Challenges

The challenges — read them online

No clone, no account — click a checkpoint to read the full challenge on its own page.

A report is a contract with the reader

Trace every number the report must carry back to its source field in results.json.

Checkpoint l01 · 10 pts · read online →02

Structure before prose

Decide the skeleton — title, section order, metrics block — before writing any prose.

Checkpoint l02 · 10 pts · read online →03

Build and render the report

Implement the contract in starter/report.py — metrics carried unchanged, sections in order, numbers formatted.

Checkpoint l03 · 10 pts · read online →04

Numbers traceable to inputs

Every metric equals its source field — the audit answer is a field name, not an explanation.

Checkpoint l04 · 10 pts · read online →05

What report verification cannot see

The suite checks structure and numbers, not insight or honesty — write the boundary sentence.

Checkpoint l05 · 10 pts · read online →

Start

How the run works

Your agent drives; the files arrive through the Skill — no download, no clone.

SkillAny coding agent

The Skill does the fetching

The sentence above starts the course: your agent walks you through the one-time authorization link (compare the code, click Allow), fetches this course's files, and drives the challenges with you. Agents without the Skill installed can work from this brief instead:

Work on the FlyPython challenge "From Analysis to Report with an Agent" (course id course-da-report).
Machine-readable brief: https://flypython.com/api/challenges/da-report
Open the course folder and read TASK.md first — it is the contract.
Rules: smallest change, no new dependencies, never edit tests/ or solution/.
Check with python verify.py until its gates pass, then report each claim code to me.

Your agent works under the task contract: smallest change, no new dependencies, never edit solution/. Optional guided mode: COURSE.md.

Files

Files come to you

Course files live at /api/challenges/da-report/files — your agent fetches the manifest and writes each file at its path. There is nothing to download by hand.

How "done" is decided →

Scenario skins

Same skills, a domain you recognize

All three skins run through the same code and the same tests. Pick the one closest to your job before lesson 1.

scenario/analysis-pack/results.json

Verified analysis pack

A verified EDA summary that your report must trace, not recompute.

Verification

How “done” is decided

Six-test contract suite: required headings in order, metrics matching inputs exactly, report files written. The starter must reproduce the unfinished state.

python verify.py  # from the course folder: checkpoint status + claim codes

Apply this to your own project

Lesson 5 ports the workflow — not the code — to one script you actually own: a three-line task contract, one new failing test made to pass, and a written record of what the tests do not prove. The same loop is described in the AI coding workflow guide and practiced by therunnable examples.

Claim your evidence

When a checkpoint passes, python verify.py prints a deterministic claim code. Your authorized agent submits them for you in one batch; by hand, paste them on yourprogress page — worth 10 points per checkpoint and theReport Challenger course badge at five. Claim codes are self-reported evidence, not certificates.

What verification does not prove

Passing the course suite proves the pinned behaviors on the tested inputs — not correctness on tomorrow’s data, not production performance, and not anything about your own project until you write its contract. Repository tests are evidence, not your outcome.

Report teaching drift ↗All courses →