Ваша AI-идентичность и ваша AI-команда, которые работают на любой AI-платформе.
Войти Начать
Меню
Создать Agent of Me Обзор стилей Профессиональные агенты Агенты сообщества Рейтинг Новости об AI
AI-платформы Каталог Model Matrix Сравнить Какой AI мне использовать? Руководства по интеграции Настроить OpenClaw Prompt Fit
Обучение и инструменты Обучение Запрос к данным Конструктор агентов API
О сайте О нас Контакты Дисклеймеры
Войти Начать
Аккаунт
Ваша AI-идентичность, всегда с вами

Создайте бесплатный аккаунт и постройте свой профиль. По умолчанию всё приватно. Ничего не публикуется без вашего согласия.

Начать Войти
Тёмная тема

🧭 Режим с подсказками
Не знакомы с prompt, system instructions, context window, token? Мы объясняем каждый термин прямо при просмотре, простым языком. Те же страницы, со встроенными подсказками.

⚡ Экспертный режим
Вы уже знаете, как работает prompting. Только суть, чётко и компактно, без лишних пояснений. Это вид по умолчанию.

Язык интерфейса

The Working Prompter · Раздел 1/5, Roles That Actually Work

Цели обучения
Нажмите «Далее» (или используйте стрелки), чтобы переходить по одной идее за раз. Таймера нет, тест из 5 вопросов ждёт в конце. Стрелка ← вверху выходит в любой момент; прогресс сохраняется.

'Act as an expert' is a costume, not a brief

'You are a world-class marketing expert' rarely changes the substance of an answer. 'Expert' fits a thousand different people with a thousand different opinions, so the model plays the average of them, and the average expert sounds a lot like the assistant you already had. Stacking prestige adjectives ('brilliant, legendary, award-winning') polishes the register at best; it adds no information.

The problem is not that role-play fails. It's that the label is empty. Everything that makes a real expert useful (what they refuse to ship, who they write for, what they check first) is left for the model to guess. The fix is to stop naming the costume and start writing the brief.

The formula: role + standards + audience + stakes

A working role spells out what the title implies. 'You are a senior editor at a trade magazine. Standards: numbers over adjectives; cut anything a busy reader would skip. Audience: plant managers who know the machines but not the jargon. Stakes: this goes to print under our name.' Four short lines, and the model now has decisions to apply instead of a character to wear.

Each part does a job. The role sets the lens. The standards define what good means. The audience calibrates detail. The role says who is writing, the audience says who they write FOR. The stakes set the error tolerance: a to-print piece and a whiteboard brainstorm deserve different strictness.

Where personas pay: judgment and register

Personas earn their keep where the task has taste in it: how a careful security reviewer would push back on a design, how a support lead delivers bad news without over-apologizing, what a skeptical CFO questions first in a forecast. Judgment calls and register are exactly what a well-specified role changes.

On mechanical tasks, a persona is decoration. 'You are a meticulous paralegal' does not extract dates from a contract any better than 'extract every date, one per line, with its source sentence.' The test: if swapping in a different role would produce the same output, the role is not doing work, spend those words on the instruction instead.

Give the role opinions and a quality bar

A neutral advisor hedges: 'you could do A or B, depending.' An opinionated role decides: 'You believe most decks are twice as long as they should be; you cut ruthlessly and list what you cut.' Opinions turn a menu of options into an editorial stance, the pushback you actually wanted from an expert.

Then hand the role a quality bar it can enforce: 'reject any headline the reader couldn't repeat from memory,' 'flag every claim with no number behind it.' You stay the editor, 'keep slide 4 anyway' overrules the persona, but disagreement is now visible instead of averaged away.

Мини-квиз, Roles That Actually Work

5 вопросов, каждый раз выбираются из банка случайно. Проходной балл 60%. Неограниченные попытки.

Следующий раздел: Showing Beats Telling →
Читать полный текст урока

1. 'Act as an expert' is a costume, not a brief

'You are a world-class marketing expert' rarely changes the substance of an answer. 'Expert' fits a thousand different people with a thousand different opinions, so the model plays the average of them, and the average expert sounds a lot like the assistant you already had. Stacking prestige adjectives ('brilliant, legendary, award-winning') polishes the register at best; it adds no information.

The problem is not that role-play fails. It's that the label is empty. Everything that makes a real expert useful (what they refuse to ship, who they write for, what they check first) is left for the model to guess. The fix is to stop naming the costume and start writing the brief.

2. The formula: role + standards + audience + stakes

A working role spells out what the title implies. 'You are a senior editor at a trade magazine. Standards: numbers over adjectives; cut anything a busy reader would skip. Audience: plant managers who know the machines but not the jargon. Stakes: this goes to print under our name.' Four short lines, and the model now has decisions to apply instead of a character to wear.

Each part does a job. The role sets the lens. The standards define what good means. The audience calibrates detail. The role says who is writing, the audience says who they write FOR. The stakes set the error tolerance: a to-print piece and a whiteboard brainstorm deserve different strictness.

3. Where personas pay: judgment and register

Personas earn their keep where the task has taste in it: how a careful security reviewer would push back on a design, how a support lead delivers bad news without over-apologizing, what a skeptical CFO questions first in a forecast. Judgment calls and register are exactly what a well-specified role changes.

On mechanical tasks, a persona is decoration. 'You are a meticulous paralegal' does not extract dates from a contract any better than 'extract every date, one per line, with its source sentence.' The test: if swapping in a different role would produce the same output, the role is not doing work, spend those words on the instruction instead.

4. Give the role opinions and a quality bar

A neutral advisor hedges: 'you could do A or B, depending.' An opinionated role decides: 'You believe most decks are twice as long as they should be; you cut ruthlessly and list what you cut.' Opinions turn a menu of options into an editorial stance, the pushback you actually wanted from an expert.

Then hand the role a quality bar it can enforce: 'reject any headline the reader couldn't repeat from memory,' 'flag every claim with no number behind it.' You stay the editor, 'keep slide 4 anyway' overrules the persona, but disagreement is now visible instead of averaged away.

Деловая активность

Business AnalystChief of StaffExecutive AssistantM&A AnalystManagement ConsultantOperations AnalystProject ManagerRecruiter

Финансы

AccountantDue Diligence AnalystEquity Research AnalystFamily Office AnalystFinancial AnalystFixed Income AnalystInvestment Banking AnalystPortfolio Analyst

Юридическое

Contract Review AssistantLegal Due Diligence AssistantLegal Research AssistantParalegal

Маркетинг

Brand StrategistContent StrategistGEO AnalystMarketing StrategistSEO AnalystSales Strategist

Личное

Career CoachLearning TutorReflection AssistantResearch AssistantTravel PlannerWriting Assistant

Недвижимость

Acquisition AnalystAsset Management AnalystCommercial Real Estate AnalystDevelopment AnalystLease AnalystProperty Financial Analyst

Исследование

Competitive Intelligence AnalystDeep Research AnalystIndustry Research AnalystJournalist ResearcherMarket Research AnalystMedical Research Assistant

Технологии

AI Strategy AdvisorCybersecurity Research AssistantData AnalystProduct ManagerSoftware Engineer