Skip to content
Last Dictionary

prompt engineer

nounAlso: prompt designer, AI whisperer

In plain wordsA person whose job is writing and testing the instructions given to AI models so they behave reliably; hyped in 2023 as a six-figure job anyone could learn, the role has since largely merged into ordinary engineering.

  1. A practitioner who specializes in prompt engineeringprompt engineering, n.: The skill of writing requests to an AI — picking the words, examples, format and background information it receives — so that it reliably gives the result you want, without retraining it.: designing, testing and maintaining the instructions, examples and context given to large language modelslarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. so that they perform tasks reliably. The work includes writing system promptssystem prompt, n.: Background instructions given to a chatbot before the conversation starts, setting its role, rules, tone and tools. Users usually never see it, but it shapes every reply., building evaluation sets to compare prompt variants, diagnosing failure modes and documenting model quirks. In 2023 the title became an emblem of the generative-AI boom, with well-publicized job postings offering salaries above US$300,000 and predictions that it would be the job of the decade; skeptics countered that better models would make prompting easy or automatic. By 2025 the skills had largely been absorbed into software, product and research roles, and attention had shifted to context engineeringcontext engineering, n.: Managing an AI model's reading material: choosing, trimming and arranging the instructions, documents, tool results and memories it is given on every turn, so that it has what the task needs and little else. and agent design.

    We don't hire prompt engineers anymore; every engineer is expected to write and evaluate prompts.

Origin

'Prompt engineering' was in use among GPT-3 users by 2021, and 'prompt engineer' appeared on AI-art and developer forums around 2021–2022. The title reached mainstream news in early 2023 through reporting on high-paying roles, notably an Anthropic posting for a 'Prompt Engineer and Librarian' with a salary range reaching US$335,000.

Usage note

Sometimes used mockingly for overstated expertise in phrasing requests to chatbots. The role's rise and fall is often cited as an example of how quickly AI job categories change.

Related

See also
  • prompt engineeringprompt engineering, n.: The skill of writing requests to an AI — picking the words, examples, format and background information it receives — so that it reliably gives the result you want, without retraining it.
  • context engineeringcontext engineering, n.: Managing an AI model's reading material: choosing, trimming and arranging the instructions, documents, tool results and memories it is given on every turn, so that it has what the task needs and little else.
  • system promptsystem prompt, n.: Background instructions given to a chatbot before the conversation starts, setting its role, rules, tone and tools. Users usually never see it, but it shapes every reply.
  • promptprompt, n.: The message or instructions you give an AI system — a question, a request, some examples or a document — that it responds to. Clearer prompts generally get better results.
  • English is the hottest new programming languageEnglish is the hottest new programming language, phr.: A catchphrase meaning that people can now get computers to do things by describing what they want to an AI in ordinary language, instead of writing code.
  • vibe codingvibe coding, n.: Programming by conversation: you ask an AI for what you want, try out what it produces and ask again until it works, trusting the code without really reading it.

Mentioned in

prompt engineeringprompt engineering, n.: The skill of writing requests to an AI — picking the words, examples, format and background information it receives — so that it reliably gives the result you want, without retraining it., AI engineerAI engineer, n.: A software developer who builds products using ready-made AI models — connecting them to data and tools and testing that they work well — rather than inventing or training the models.