← Back to prompts
SalesAccount Executivebeginner 5 min saved

Professional Conversation Restarter

Draft concise, low-pressure follow-up messages to re-engage stakeholders without using guilt trips or sales fluff.

Customise & copy

Add the context you have. The prompt updates as you work.

The name or identifier of the recipient.

The topic or history of the previous communication.

The desired next step from the original exchange.

Live prompt

3 fields
Draft a professional, concise, and low-pressure follow-up message to restart a stalled conversation. 

Recipient: Alex
Context of previous conversation: Sent the Q3 marketing proposal last Tuesday.
Intended goal or next step: Get feedback on the proposal.

Constraints:
- Do not use guilt trips, aggressive sales tactics, or passive-aggressive language.
- Avoid conversational filler, meta-commentary, and politeness padding.
- Provide a single, complete, ready-to-send draft with a clear, low-friction call to action.

Proof before you use it

A real example

Tested on gemini-3.1-flash-lite on 2026-09-04

{
  "intended_goal": "Confirm whether the budget aligns with their expectations to move forward.",
  "recipient_name": "David",
  "conversation_context": "Sent the revised Q3 digital marketing strategy proposal two weeks ago."
}

A small ritual that works

How to use it

  1. 01Enter the recipient's name.
  2. 02Provide a brief summary of the previous interaction.
  3. 03State the specific next step or goal you are seeking.
  4. 04Review the generated draft and send directly.

Why it works

The prompt structures a stalled-conversation follow-up by explicitly requiring recipient details, previous context, and an intended goal through variable inputs. It enforces constraints that block guilt trips, aggressive tactics, and filler, while demanding a single, complete draft with a low-friction call to action.

Where it fails

INSUFFICIENT_EVIDENCE

Customisation tips

Adjust the variable values for recipient_name, conversation_context, and intended_goal to reflect the precise details of the stalled exchange. Ensure the output strictly avoids conversational filler and politeness padding per the evaluator findings.

Watch-outs

  • Both test outputs failed the evaluator's check for conversational filler and politeness padding by including phrases like 'I’m checking in to see if'.
  • Drafts must be closely checked against the negative constraints to ensure phrases like 'I am happy to' or similar padding are completely removed.

Works in

ChatGPTClaudeGemini

Was this useful?

Submit your variation

If your version helps, it may be published with your name and a link back to you.

Want to make AI useful across your team? Explore Atul's training.