Subject areaChannels and tools
A query is the question a person puts to a system to retrieve information that already exists: the words typed into a search engine, a request to a database (an organised store of data), a filter in management software.
The system creates nothing. It searches, selects and ranks what it finds.
The word comes from the Latin *quaere*, "ask", the imperative of the verb *quaerere*, "to seek, to ask". In computing, the query took hold in the 1970s with languages for querying databases: in 1974 Donald Chamberlin and Raymond Boyce, IBM researchers, presented SEQUEL, which became SQL. In 1990 Alan Emtage, a student at McGill University in Montréal, created Archie, considered the first Internet search engine: since then a query is also what we type into a search box. Queries are the raw material of SEO: every page that ranks answers a query.
## Query and prompt: what they share, what sets them apart
Both are questions put to a machine, and in both the quality of the answer depends on the quality of the question. The differences lie in what is asked and in who carries responsibility for the answer.
<figure class="eg-tabella"><table><caption>Query and prompt compared</caption><thead><tr><th></th><th><a href="/en/glossary/query">Query</a></th><th><a href="/en/glossary/prompt">Prompt</a></th></tr></thead><tbody><tr><td>What it asks</td><td>To <strong>find</strong> what exists</td><td>To <strong>produce</strong> what does not exist yet</td></tr><tr><td>What it returns</td><td>A list of sources to choose from</td><td>A finished text, image or analysis</td></tr><tr><td>Typical form</td><td>A few keywords</td><td>Sentences, context, role, examples, constraints</td></tr><tr><td>Who interprets</td><td>The person, who reads the sources and decides</td><td>The machine interprets first, the person checks afterwards</td></tr><tr><td>Main risk</td><td>Stopping at the first result</td><td>Taking a plausible but invented answer as true</td></tr><tr><td>What stays with the company</td><td>Knowing where to look</td><td>Knowing how to give context: values, data, goals</td></tr><tr><td>When it emerged</td><td>1970s (databases), 1990 (web)</td><td>Spread from 2020 with large language models</td></tr></tbody></table></figure>
With a query you ask the machine to show where the answer is. With a prompt you ask it to write the answer. Moving from one to the other puts a new responsibility on the person: what used to be chosen among several sources must now be checked in a single answer.
An example
A purchasing manager types «CRM software for manufacturers» into a search engine. The engine does not write an answer for them: within a fraction of a second it returns a list of existing pages, ranked by how relevant it judges them.
broader entriesthis entry and narrowertwo levels down← up · → down
Enrico Giubertoni. Licensed under CC BY-NC 4.0: you may quote, translate and adapt this entry with the author’s name and a link, stating any changes. For commercial use, write to info@enricogiubertoni.com
Spotted an inaccuracy or something that needs updating? Write to info@enricogiubertoni.com and help make this glossary a better place.
What are your business challenges?
Tell us about your priorities and the objectives you want to reach.
You will receive a free, targeted answer within one working day.