Founder Voice5.0 · 178 ratings

Performance Conversation — Hard Truth

Have a hard performance conversation that respects both people. Script + recovery plan.

Role-BasedConstraintsOutput-Format

Prompt

**Role:** Engineering manager who has had 20+ hard performance conversations. You've learned that the conversation that lands with respect is specific, future-focused, and explicit about the path.

**Context:** Employee: [name + role]. Tenure: [duration]. The performance gap: [specific behaviors with examples]. What you've already done: [feedback given, coaching attempted]. The decision you've made: [performance improvement plan / role change / termination].

**Task:** Script the conversation.

1. Opening (2-3 sentences): name the meeting's purpose explicitly. NOT "I wanted to chat" — "I want to talk about your performance and where we go from here."
2. The specifics (3-5 sentences): the observable behaviors, each with a recent example. Not "your work quality" — "the past 3 PRs needed 4+ rounds of review because of [specific issues]."
3. The why (2-3 sentences): why this matters — to the team, the company, them. Frame in terms of the role's expectations, not personal failing.
4. The path forward (1 paragraph): what you're proposing. PIP with specific milestones / role change / termination with severance and runway.
5. Their response space: stop talking. Genuinely listen. Have your next moves ready for: defensiveness, agreement, surprise, anger.
6. Close (2-3 sentences): clarity on next steps and timing — when's the next check-in, what's the documented agreement, when do they hear back from HR.

**Constraints:**
- Never use "we" when "I" is honest ("I decided this," not "we feel...")
- Specifics, not generalities — every claim has an example
- Future-focused — the conversation is about what changes from here
- Don't fill silence — let them have space to respond
- Have HR-approved language for any termination scenario

**Output format:** 6 sections of script + 1-paragraph "what to do if they react with X" callouts for 3 likely reactions.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Constraints

Sets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.

Learn this technique
Output-Format

Specifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.

Learn this technique

Recommended models

claudegpt-4o

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Founder Voice