ChatGPT prompts for ecommerce
این پرامپت برای ساخت پیام تبلیغاتی که واقعاً فروش میآورد نوشته شده است. چیزی که از مدل میخواهد: «These ecommerce prompts cover product listings and descriptions, customer acquisition and retention, promotional campaigns, and the tracking and analytics that…»
متن پرامپت
These ecommerce prompts cover product listings and descriptions, customer acquisition and retention, promotional campaigns, and the tracking and analytics that support decisions. Complementary product recommendations: Recommend [number] products from this list that complement [item]. Rank them by verified compatibility and use case, and briefly explain each match. Do not assume features or customer behavior not provided. Product list: [Insert product list]. Style example: [Insert example] Product descriptions: Write a 50-word description for [product] aimed at [audience]. Highlight verified features, benefits, and differentiators in a [tone] voice. Use these keywords only where natural: [Insert keywords]. Product details: [Insert information]. Style example: [Insert example] Chatbot messaging: Write a friendly chatbot message of about 50 words explaining [company]’s return policy. Include the exact return window, conditions, refund method, and next step without omitting important restrictions. Policy: [Insert return policy]. Brand voice: [Insert information]. Style example: [Insert example] Ecommerce tracking setup: Using current Meta documentation, explain how to track [event] on [ecommerce platform] with Meta Pixel and Conversions API. Cover browser and server setup, parameters, consent, event deduplication, testing, and troubleshooting. If you cannot verify current documentation, say so and note which steps may have changed. Context: [insert technical details] Product comparison chart: Create a neutral comparison of [product] and [competitors] covering price, features, limitations, and representative customer feedback, using the product and competitor information provided. Apply the same criteria to each, and where information is missing, mark it as unknown rather than estimating. If you have browsing access, you may supplement with cited, dated sources. Product and competitor information: [insert details] Product listing optimization: Rewrite these product titles using [keywords] naturally while preserving product accuracy and brand voice. Keep each under 60 characters as an editorial limit and provide the character count, noting it should be verified before publishing. Product list: [paste list]. Brand context: [insert information]. Style example: [insert example] Newsletter signup emails: Suggest [number] email concepts encouraging eligible customers to subscribe for [newsletter benefits]. For each, include the angle, subject line, value proposition, and CTA. Context: [insert information] Retargeting ad copy: Write [number] ad variations for [abandoned-cart or product-view] audiences. Highlight verified benefits and use urgency only when supported by a real deadline or availability constraint. Include primary text, headline, and CTA. Context: [Insert audience, product, and offer details] CTA generation: Write [number] two-to-four-word CTA buttons for [page or action], aimed at [audience]. Vary the intent and tone; use urgency only where genuine. Style example: [Insert example] Loyalty program ideas: Suggest [number] loyalty-program concepts for [business and audience]. For each, include earning and redemption rules, customer value, business cost, success metrics, and fraud or compliance risks. Flag rewards involving reviews or social endorsements. Product collection descriptions: Write [number] [word-count]-word collection descriptions for [brand and collections], targeting [audience]. Explain what the collection includes and its main value, using [keywords] naturally. Brand and product information: [Paste details] SMS campaign: Write a [number]-message SMS campaign for consenting customers in [market], promoting [product]. Include timing, sender identification, CTA, and required opt-out wording. Keep offer terms accurate and use emojis only if they fit the brand. Product details: [Paste information] Back-in-stock emails: Draft a [number]-email back-in-stock sequence for customers who requested alerts for [product]. Cover the restock announcement and a follow-up for those who haven't purchased, and note limited availability only if the supplied inventory information supports it. For each email, include the subject, body, CTA, and send timing from the restock date. Use only verified product and inventory details: [insert product and inventory details] Cart abandonment sequence: Write a [number]-email cart-abandonment sequence for [product category]. Include the subject, body, CTA, and delay from abandonment. Use only the supplied offer terms and avoid false urgency or availability claims. Context: [insert details] Social media contest ideas: Suggest [number] contest concepts for [platform, audience, and market]. For each, include the entry mechanic, prize, content format, participation CTA, and measurement goal. Flag platform-rule, legal, disclosure, and content-rights considerations. Brand context: [Paste information] Product demo video script: Write a [duration] product-demo script for [platform] showing how [product] helps [audience] with [use case]. Include timestamps, narration, demonstrations, visual cues, and a CTA. Use only verified functionality. Product information: [Paste details] Comparison blog post: Write an evidence-based comparison of [product] and [competitor] for [audience]. Compare the same criteria, including features, price, limitations, and representative reviews. Cite and date all external information, distinguish facts from judgments, and avoid unsupported superiority claims. Context: [Paste information] Ecommerce product quiz: Using current documentation for [ecommerce platform/CMS], provide a beginner-friendly guide to build a product recommendation quiz for [collection]. Cover questions, recommendation logic, implementation, testing, analytics, accessibility, data handling, tools, costs, and assumptions. If you cannot verify current documentation, say so and note which steps may have changed. For marketplace keyword research, Ecommerce Keyword Analytics shows search, click, order, and conversion data across supported online retailers. It requires a separate App Center subscription.
چطور از این پرامپت استفاده کنم؟
این یک پرامپت در سطح «پیشرفته» از دسته مارکتینگ و فروش است. برای اینکه بهترین نتیجه را بگیری، این مسیر را دنبال کن:
۱) کپی کن. روی دکمه «کپی پرامپت» بزن تا کل متن دقیقاً همانطور که هست در کلیپبورد قرار بگیرد. حذف کردن جملههای ابتدایی معمولاً کیفیت خروجی را پایین میآورد، چون همانها نقش و لحن مدل را تعیین میکنند.
۲) در یک گفتگوی تازه بچسبان. این پرامپت را به عنوان اولین پیام یک چت جدید بفرست. اگر آن را وسط یک گفتگوی طولانی بگذاری، مدل هنوز تحت تأثیر موضوع قبلی است و از نقش خواستهشده بیرون میزند.
۳) بلافاصله بعد از آن، موضوع خودت را بنویس. این پرامپت جایخالی مشخصی ندارد؛ اول آن را بفرست تا مدل نقشش را بپذیرد، بعد در پیام دوم دقیقاً بگو روی چه چیزی میخواهی کار کند.
۴) به مدل زمینه بده. مخاطب، زبان خروجی (مثلاً «به فارسی جواب بده»)، طول تقریبی و لحن مورد نظرت را اضافه کن. بیشتر جوابهای ضعیف نتیجه نبودِ همین سه خط اضافهاند، نه ضعف خودِ پرامپت.
۵) یک بار اصلاح کن. جواب اول را نهایی فرض نکن. بنویس «این بخش را کوتاهتر کن»، «مثال واقعی اضافه کن» یا «سه نسخه متفاوت بده». دور دوم تقریباً همیشه بهتر از دور اول است.
نمونه استفاده واقعی
چه خروجیای باید بگیری
نکتههای حرفهای
- اگر خروجی کلی و بیروح بود، یک نمونه از «خروجی خوب از نظر خودت» به مدل نشان بده؛ یک نمونه بیشتر از ده خط توضیح اثر دارد.
- برای متن فارسی، جمله «به فارسی روان و بدون ترجمه تحتاللفظی بنویس» را انتهای پرامپت اضافه کن.
- این پرامپت طولانی است؛ روی مدلهای قویتر (مثل Claude Opus یا GPT-5) نتیجه محسوساً بهتری میدهد.
- مخاطب هدف را با جزئیات بنویس؛ «زن ۳۰ تا ۴۰ ساله علاقهمند به دکور دستساز» خیلی بهتر از «مشتری عادی» جواب میدهد.