Content template
Meeting summary prompt template
Decisions, owners, and deadlines from a transcript. Sharing outcomes with people who missed a meeting, where invented action items would do more harm than a short summary.
The prompt
prompt.md
## Task
Summarize the meeting transcript below for people who did not attend.
## Requirements
- Only include decisions and action items stated in the transcript.
- Name an owner and a due date for each action item, or write "unassigned".
## Output format
Return markdown under 200 words with three sections: Decisions, Action items, and Open questions. Use bullet points in each section.
## Input
<transcript>
{{transcript}}
</transcript>Variables
| Variable | What to pass in |
|---|---|
{{transcript}} | The meeting transcript or detailed notes. |
Each variable sits inside its own tags so the model treats what you insert as data, not instructions.
How it scores
100/100 with no warnings or critical issues, checked in CI on every change.
| Dimension | Score |
|---|---|
| Clarity | 100 |
| Specificity | 100 |
| Completeness | 100 |
| Structure | n/a |
| Consistency | 100 |
| Output specification | 100 |
| Efficiency | 100 |
| Security | 100 |
Tokens and cost per model
Input tokens for the template itself, before you fill in the variables. Costs use reference prices; verify with your provider.
| Model | Tokens | Input cost / 1,000 calls |
|---|---|---|
| GPT-4.1 | 96 | $0.1920 |
| GPT-4.1 mini | 96 | $0.0384 |
| Claude Sonnet 5.5 | 96 (approx.) | $0.1920 |
| Claude Haiku 4.5 | 96 (approx.) | $0.0960 |
| Gemini 2.5 Flash | 96 (approx.) | $0.0288 |
Adapting it
- Rename the three sections to match your team (for example Decisions, Risks, Next steps).
- Raise the word limit for long meetings instead of removing it.
- Add "Use the participant names as written in the transcript" if names are ambiguous.
After editing, the workspace re-scores the prompt as you type and flags anything that regresses.
More templates
- Pull request review: Structured review of a diff with severity-ranked findings.
- Customer support reply: On-policy reply to a customer ticket with a fixed structure.
- Structured data extraction: Extract fields from free text into a strict JSON object.
- Ticket classification: Route a message to exactly one category with a confidence.
- Tool-using agent system prompt: Scoped agent with explicit tool rules and a stop condition.