Micro-internship brief ≈14h across 5 days — set up the script, then twice-daily runs and fixes for 5 daysbuilder

Collect your city’s air quality data by script for 5 days

Level up from downloading datasets to collecting them: write a small script (AI-assisted) that pulls your city’s live air quality or weather data on a schedule for 5 days, then analyse what you gathered.

Data AnalysisContent StrategyData VisualisationPython for DataAnalytical Reasoning

Posted by The AI Internships

The work brief

01Pick a free data source for your city: data.gov.in AQI API, OpenAQ, or Open-Meteo (no key needed).
02Write the script (Python/Node) with AI as pair-programmer — let it draft the fetch-and-append code, then read every line until you can explain it. Run it at least twice daily for 5 days — manually, scheduled, or via GitHub Actions.
03Expect breakage: the API will fail, the format will surprise you. Log what broke and how you fixed it.
04Analyse the collected data: daily patterns, best/worst times, comparison with official summaries. Push script + data to a public repo.

What you’ll produce

5 deliverables

Submission standard

Submit the repo (script + collected CSV), the collected data pasted as CSV, your breakage log, and the analysis with a chart. Include your AI workflow — tools, best prompts, and what you changed. Include a dated screenshot of the live source reading, and make sure your CSV timestamps span the 5 days and match your repo's commit history.

Public repo with your collection script and the raw CSV
Public repo with the script and raw CSV; the commit history should show runs spread over the 5 days, not one bulk upload.
Public linkRequired
Your collected readings as CSV (timestamp, metric, value)
timestamp, metric, value — readings must span 5 days at 2+ per day; real API data has gaps and surprises, so show them.
CSV dataRequired
What broke during collection and how you fixed it
Written responseRequired
Your analysis: patterns, best/worst times, anything that contradicts expectations
Written responseRequired
A chart of your collected data over time
Image uploadRequired

You’ll complete these inside your private workspace.

What you must submit as proof

This brief requires evidence an AI can’t fabricate.

Dated screenshot of the live API/source reading for your city on one collection day (e.g. the OpenAQ/Open-Meteo response or portal)
Show the real source value at a given timestamp so one CSV row can be checked against it.
Image uploadRequired

Submissions without this evidence cannot be submitted.

Protect other people in your proof. Blur faces, names, phone numbers and email addresses before you upload, and refer to anyone you worked with by role or number ("Listener 1", "the stall owner"). Your proof is only ever used to check your work — it is never published, never appears on your certificate, and is never shown in your public portfolio.

How your work is evaluated

The passing benchmark is 70/100.

Scripted collection

29%

A real script collected real multi-day readings (timestamps prove it).

Debugging honesty

29%

The breakage log shows real problems really solved.

Analysis

14%

Findings follow from the collected data.

Timestamps ↔ commits ↔ source

29%

CSV timestamps must span 5 days and reconcile with the repo's commit history and the dated source reading. A single bulk commit, flat readings, or a CSV that cannot be traced to the source is a fail.

How we grade your AI usage

30% of your score

Using AI is the point — it’s the skill this certificate proves. You’ll answer three short questions about how you used it: what you asked, what was wrong with its first answer, and what you changed. Specific, honest answers score high. “I pasted the brief and submitted the answer” scores near zero.