Prompt library
Summarize a campaign debrief
Separating targeted metrics from observed ones blocks retroactive goal-setting, the most common debrief distortion. The bad-bet versus bad-execution split routes each failure to the right fix, and will/stop phrasing turns lessons into commitments instead of sentiment.
Last reviewed July 17, 2026
The prompt
Summarize this campaign into a debrief the next campaign can learn from.
Campaign data and notes: {{data}}
Sections:
1. Scoreboard: goal vs actual for every metric we set a target on, in a table. Metrics without a pre-set target go in a separate "observed" table so hindsight does not masquerade as planning.
2. What worked: max 3 items, each with the number that proves it and the mechanism you believe explains it.
3. What failed: max 3 items, same discipline. State whether each failure was a bad bet or bad execution; the fix differs.
4. Surprises: anything the data shows that we did not have an opinion about beforehand.
5. Decisions for next time: each phrased as "we will / we will stop", owner role attached. No "we should consider".
If the data cannot support a claim in my notes, say so rather than repeating it.Run in idaptOpens a new chat with the prompt prefilled. Nothing sends until you press send.
Fill in the variables
| Variable | What it is | Example |
|---|---|---|
| {{data}} | Metrics export plus your notes on what happened | [paste campaign metrics and your running notes] |