Persona prompting

Persona prompting is the practice of assigning the model a specific identity, expertise, and audience in the system prompt to steer voice, tone, and answer depth.

Persona prompting works in 2026 — but more subtly than the 2023 "you are a world-class expert" cargo cult. Strong personas combine a role ("senior contract lawyer"), an audience ("explaining to a non-lawyer founder"), and a constraint ("flag liability-shifting clauses only"). Vague persona prompts ("act as an expert") show no measurable benefit on frontier models. Strong, specific personas measurably improve tone, lexical choice, and answer scope. As a rule: if a real human would interpret the persona differently from "a thoughtful generalist", the persona is doing work.

When to use persona prompting

• Steering tone, register, or audience.
• Domain-specific output (legal, medical, code review).

Common mistakes

• Vague "you are an expert" — no measurable benefit on frontier models.
• Persona that conflicts with the task — the model picks one and ignores the other.

FAQ

Related terms

• System prompt — A system prompt is the high-priority instruction block that defines a model's role, constraints, and default behaviors for an entire conversation.
• Prompt engineering — Prompt engineering is the practice of designing input text that reliably steers a large language model toward a specific output.
• Few-shot prompting — Few-shot prompting supplies 2–10 input–output examples inside the prompt so the model imitates the pattern on a new input.

Last updated: 2026-06-01. Raw markdown: https://promtable.com/glossary/persona-prompting.md.