Skip to main content
Back to Library
Prompt Engineering Guide

Mastering Write email
on DeepSeek V3

Stop guessing. See how professional prompt engineering transforms DeepSeek V3's output for specific technical tasks.

The "Vibe" Prompt

"Hey, write an email for me. I need to tell my team about the new project timeline. It's pushed back. Make it sound professional but also understanding. Include the new dates."
Low specificity, inconsistent output

Optimized Version

STABLE
{ "task": "Generate an email to the project team.", "recipient": "Project Team", "sender": "[Your Name/Role]", "purpose": "Communicate a revised project timeline.", "key_information": [ { "point": "Original project completion date was [Old Date].", "status": "Delayed" }, { "point": "New project completion date is [New Date].", "status": "Confirmed" }, { "point": "Reason for delay: [Brief reason, e.g., 'unforeseen technical challenges', 'resource reallocation', 'client feedback'].", "status": "Contextual" }, { "point": "Impact: [Briefly mention positive outcome of delay, e.g., 'ensuring higher quality', 'allowing for comprehensive testing', 'incorporating valuable feedback'].", "status": "Positive Spin" } ], "tone": "Professional, understanding, and reassuring while maintaining clarity.", "call_to_action": "Encourage questions and offer support (e.g., 'Please review the updated schedule and reach out with any questions or concerns').", "formatting": "Standard email structure with clear subject line, salutation, body paragraphs, and closing.", "subject_line_options": [ "Update: [Project Name] Timeline Adjustment", "Important: Revised Timeline for [Project Name]", "[Project Name] - Revised Completion Date" ] }
Structured, task-focused, reduced hallucinations

Engineering Rationale

The optimized prompt leverages a structured JSON format, explicitly outlining all necessary components for email generation. It uses a chain-of-thought by breaking down the complex 'email writing' task into smaller, manageable attributes like 'recipient', 'purpose', 'key_information' (with sub-statuses), 'tone', and 'call_to_action'. This structured approach guides the model to systematically construct the email, ensuring all critical elements are addressed and presented coherently. The 'key_information' array with 'point' and 'status' forces a detailed inclusion of information, differentiating between old and new dates and providing context for the delay and its positive spin. It also offers specific subject line options, reducing ambiguity. This contrasts with the vague 'vibe' prompt, which relies heavily on the model's interpretation of 'professional but understanding' and doesn't explicitly ask for specific details like the reason for delay or a positive spin, leading to potentially generic or incomplete outputs.

0%
Token Efficiency Gain
The optimized prompt explicitly asks for new dates, which the naive prompt implicitly does.
The optimized prompt defines the desired tone precisely, whereas the naive prompt uses a conversational tone.
The optimized prompt breaks down the 'what to include' into a structured list, improving clarity.

Ready to stop burning tokens?

Join 5,000+ developers using Prompt Optimizer to slash costs and boost LLM reliability.

Optimize My Prompts