AI identity và AI team của bạn, portable trên mọi nền tảng AI.
Đăng nhập Bắt đầu
Menu
Xây dựng Agent of Me Khám phá Phong cách Professional Agents Agent cộng đồng Bảng xếp hạng Tin tức AI
Nền tảng AI Danh mục Model Matrix So sánh Tôi nên dùng AI nào? Hướng dẫn tích hợp Thiết lập OpenClaw Prompt Fit
Học & Công cụ Học Hỏi dữ liệu Agent Builder API
Giới thiệu Về chúng tôi Liên hệ Tuyên bố miễn trách
Đăng nhập Bắt đầu
Tài khoản
AI identity của bạn, mang đi được

Tạo tài khoản miễn phí để xây dựng profile của bạn. Mặc định riêng tư. Không có gì được chia sẻ trừ khi bạn tự công bố.

Bắt đầu Đăng nhập
Chế độ tối

🧭 Chế độ hướng dẫn
Chưa quen với prompt, system instruction, context window, token? Chúng tôi giải thích từng thuật ngữ ngay khi bạn duyệt, bằng ngôn ngữ dễ hiểu. Cùng một trang, tích hợp sẵn phần hướng dẫn.

⚡ Chế độ chuyên gia
Bạn đã biết cách prompting hoạt động. Chỉ phần nội dung thực chất, gọn gàng và súc tích, không có giải thích thêm. Đây là chế độ xem mặc định.

Ngôn ngữ giao diện

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

Mục tiêu học tập
Nhấn Next (hoặc dùng phím mũi tên) để chuyển từng ý một. Không giới hạn thời gian, bài kiểm tra 5 câu chờ ở cuối. Mũi tên ← ở trên cùng thoát bất cứ lúc nào; tiến trình được giữ lại.

'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.

Câu đố nhanh, Roles That Actually Work

5 câu hỏi, được rút ngẫu nhiên từ ngân hàng đề mỗi lần thử. Điểm đạt 60%. Làm lại không giới hạn.

Phần tiếp theo: Showing Beats Telling →
Đọc toàn bộ văn bản bài học

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.

Doanh nghiệp

Business AnalystChief of StaffExecutive AssistantM&A AnalystManagement ConsultantOperations AnalystProject ManagerRecruiter

Tài chính

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

Pháp lý

Contract Review AssistantLegal Due Diligence AssistantLegal Research AssistantParalegal

Marketing

Brand StrategistContent StrategistGEO AnalystMarketing StrategistSEO AnalystSales Strategist

Cá nhân

Career CoachLearning TutorReflection AssistantResearch AssistantTravel PlannerWriting Assistant

Bất động sản

Acquisition AnalystAsset Management AnalystCommercial Real Estate AnalystDevelopment AnalystLease AnalystProperty Financial Analyst

Nghiên cứu

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

Công nghệ

AI Strategy AdvisorCybersecurity Research AssistantData AnalystProduct ManagerSoftware Engineer