Skip to content
agentusehub

Collate WHO data into a multi-tab spreadsheet

Testers had ChatGPT Agent navigate the WHO site, extract the latest data and organise it by indicator, country and trend; it often fails on logins or dynamic pages.

Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

Testers had ChatGPT Agent navigate the WHO site, extract the latest data and organise it by indicator, country and trend; it often fails on logins or dynamic pages.

Reported experience

  1. What they did

    In ChatGPT Agent mode, the testers gave a single prompt asking it to retrieve the most recent publicly available World Health Organisation data. The agent navigated the WHO site by itself, pulled out the relevant figures and arranged them into a multi-tab spreadsheet. The tabs were sorted by indicators, countries and trends. The source doesn't describe any human steps beyond the prompt.

  2. How it went

    The source says the agent produced a clean multi-tab spreadsheet. It gives no figures on accuracy or time. It also warns that agent outputs often need reformatting or correction.

  3. Worth knowing

    Agents often fail on sites with logins, unsupported browser states or dynamic single-page apps, so check the output and be ready to fix or reformat it.

Example prompts

Try with ChatGPT Agent
Go to [data source website, e.g. WHO data portal] and pull the latest figures on [indicator] for [list of countries]. Build a spreadsheet with tabs organized by indicator, country and trend over time, with source links and the date of each data point. Finish when it's complete, and list any pages you couldn't access because of logins or dynamic content.
Research & Knowledge

Analyze 170k LLM logs overnight

A user left a Gemini agent running overnight to analyze 170k LLM logs with the llm CLI and a free model, and it finished the job despite limits.

Gemini