Cuiar
Sign inDownload

Build one table from several public statistics

Numbers from official sources in one sheet, with the same units, years and country codes.

  • You start it: When you start it
Use in CuiarRun from your AI agent

What it does

The task

Build a dataset of indicators for countries for the years years. Take each indicator from an official source: a national statistics office, Eurostat, the World Bank, the OECD or Our World in Data. Put the data in a new Google Sheet in long format: Country, ISO code, Year, Indicator, Value, Unit, Source link. Use one unit for each indicator, and convert when you must. Add a tab named Notes with each definition, each conversion and each gap.

  • It works in Our World in Data, any government site and Google Sheets, in the workspace you pick, and signs in with passwords from your Cuiar vault.
  • It runs once, when you start it.

What you give it

BlankWhat to giveExample
indicatorsThe numbers you need, separated by commasHousehold electricity price, heat pumps sold per 1,000 households, share of homes heated with gas
countriesThe countries, separated by commasGermany, France, Italy, Spain, Poland, Netherlands, Sweden, Austria
yearsThe first and the last year2015 to 2025

What you get back

An example run with the example values above. Your run uses your own data.

Dataset: 3 indicators, 8 countries, 2015 to 2025 (Google Sheet)

Rows: 252 of 264 possible

Indicators:

  • Household electricity price: EUR per kWh with taxes, Eurostat
  • Heat pumps sold per 1,000 households: national associations
  • Share of homes heated with gas: national statistics offices

Conversions: 2 countries from local currency to EUR at the yearly average rate (ECB)

Gaps: 12 cells, for example Poland heat pumps 2015 and 2016

Notes tab: 9 definitions, 4 conversions, 12 gaps

Run it in Cuiar

  1. 01

    Open it

    Click Use in Cuiar on this page. The side panel opens with the task in the composer.

  2. 02

    Fill in 3 blanks

    Type indicators, countries and years. Tab moves to the next blank.

  3. 03

    Run it

    Run sends it to the agent. Follow each step in the panel, and stop it at any time.

From the terminal

cuiar exec "Build a dataset of Household electricity price, heat pumps sold per 1,000 households, share of homes heated with gas for Germany, France, Italy, Spain, Poland, Netherlands, Sweden, Austria for the years 2015 to 2025. Take each indicator from an official source: a national statistics office, Eurostat, the World Bank, the OECD or Our World in Data. Put the data in a new Google Sheet in long format: Country, ISO code, Year, Indicator, Value, Unit, Source link. Use one unit for each indicator, and convert when you must. Add a tab named Notes with each definition, each conversion and each gap."

Run it from your AI agent

Claude Code, Codex, Cursor and other MCP clients reach Cuiar at https://mcp.cuiar.com/mcp. Add the server one time, then ask for the task in plain words, or call run_task yourself.

1. Add Cuiar to Claude Code

claude mcp add --transport http cuiar https://mcp.cuiar.com/mcp

2. Ask your agent

Use the Cuiar tool run_task to run my "Build one table from several public statistics" template with indicators = Household electricity price, heat pumps sold per 1,000 households, share of homes heated with gas; countries = Germany, France, Italy, Spain, Poland, Netherlands, Sweden, Austria; years = 2015 to 2025.

Setup for other agents: AI agents.

The tool call

{
  "name": "run_task",
  "arguments": {
    "task": "Build a dataset of Household electricity price, heat pumps sold per 1,000 households, share of homes heated with gas for Germany, France, Italy, Spain, Poland, Netherlands, Sweden, Austria for the years 2015 to 2025. Take each indicator from an official source: a national statistics office, Eurostat, the World Bank, the OECD or Our World in Data. Put the data in a new Google Sheet in long format: Country, ISO code, Year, Indicator, Value, Unit, Source link. Use one unit for each indicator, and convert when you must. Add a tab named Notes with each definition, each conversion and each gap."
  }
}

Related templates

All data templates

  • Research

    Find official statistics on a question

    The latest official numbers with the year, the definition and a link, and a short answer.

    You start it: When you start it
    • Our World in Data
    • Any government site
    • Google Sheets

  • Data

    Turn a list on a website into a sheet

    Each item from each page, one row for each, with no duplicates.

    You start it: When you start it
    • Any website
    • Google Sheets

  • Data

    List local businesses with their contacts

    Name, address, phone, website, rating and e-mail for each business.

    You start it: When you start it
    • Google Maps
    • Google Sheets

  • Data

    Export your order history

    For stores with no export: each order in a sheet, with totals for each year.

    You start it: When you start it
    • Any online store
    • Google Sheets

  • Data

    Pull tables from PDFs into a spreadsheet

    Each matching table from your PDFs and scans in one sheet, with numbers as numbers and the page noted.

    You start it: When you start it
    • Google Drive
    • Google Sheets

  • Data

    Clean up a messy spreadsheet

    Consistent names, dates, phone numbers and amounts in a new tab, with a count of each type of change.

    You start it: When you start it
    • Google Sheets