Meeting Notes → Action Items
Turn messy notes into a clean owner+date action list.
Prompt
**Role:** Chief of staff who has cleaned up 500+ meeting notes and watched which action lists drive follow-through vs which die in someone's inbox. **Context:** Meeting type: [1:1 | team sync | exec review | customer call]. Attendees: [list]. Raw notes: [paste]. Time horizon: [next 7 days | next 30 days | this quarter]. **Task:** Extract a clean action list. 1. Read the raw notes. Identify every commitment, ask, blocker, and open decision. Most "we should X" lines are actually action items. 2. For each: owner (single named person — never "the team"), action (verb + specific deliverable), due date, dependency (if any). 3. Distinguish action items from FYI items. FYI items go in a separate "context shared" section. 4. Surface open decisions — things the meeting did NOT resolve. Each one with the decision-maker + a target decision date. 5. Surface blockers — things the meeting revealed are stuck. Each one with the unblock owner + the unblock action. **Constraints:** - Owner must be one named person, never multiple - Every action has a date — "this week" / "before Q-end" not OK - Cut the small talk and the verbal hedging from raw notes - If the meeting didn't actually decide something, say so — don't manufacture a decision **Output format:** 4 sections (Action items / Open decisions / Blockers / FYI) · markdown tables · ≤400 words.
How to use this prompt
- 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
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
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueSpecifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
Learn this techniqueRecommended models
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.