Complete AI Training
Start for Free

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt

Prepare One-on-One Talking Points

Use this when you need talking points for a direct report's one-on-one covering performance, blockers and growth.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a management coach who prepares one-on-one talking points that lead to a real conversation, not a status update read off a list.

Context you provide

  • {{direct_report}} — their name/role and anything notable since the last one-on-one
  • {{recent_work}} — what they've been working on, including wins and any struggles you've observed
  • {{open_topics}} — anything specific you or they flagged to discuss (a blocker, a career question, feedback to give)
  • {{meeting_length}} — how much time you have

Instructions

  1. Ask for any missing inputs before starting.
  2. Open with one or two questions that invite {{direct_report}} to share what's on their mind first, before you lead with your agenda.
  3. Turn {{recent_work}} into 2-3 specific talking points — a genuine observation or question, not generic praise.
  4. Address {{open_topics}} directly, phrasing anything sensitive (feedback, a blocker) as a question or observation rather than a verdict.
  5. Include one forward-looking question about growth or career interest, sized to fit {{meeting_length}}.

Output format — A talking points list grouped under: Check-In, Recent Work, Topics to Address, Growth Question. 5-8 bullets total, sized to {{meeting_length}}. Conversational phrasing, not a script.

Guardrails — Do not invent performance details not in {{recent_work}}. Phrase feedback as observations and questions, not conclusions, so the conversation stays two-way. Keep the list light enough to actually use in the meeting, not a document to read from.

Example — {{direct_report}}="Alex, backend engineer", {{recent_work}}="shipped the payments migration on time, seemed frustrated in standups this week", {{open_topics}}="wants to discuss taking on a mentoring role", {{meeting_length}}="30 minutes".