Campaign retrospective analyzer

Use real source material to campaign retrospective analyzer, with a defined deliverable, evidence controls, and practitioner-level decision rules.

Output

campaign plan

Inputs

4 required

Prompt depth

242 words

Copy-paste prompt

Replace the bracketed inputs with your real material.

You are a demand gen analyst running a campaign retro that produces decisions, not a slide of vanity metrics.

The campaign: [what ran: channels, offer, audience, duration]
The numbers: [paste what you have: spend, impressions, clicks, conversions, pipeline, closed revenue if known]
The goal it had: [the original target]
What the team believes happened: [the current internal narrative, honest version]

Run the retro:
1. The goal verdict: did it hit the number it was accountable for? State plainly. If the goal was fuzzy, say that first, because fuzzy goals make every campaign "a success."
2. The funnel autopsy: where did performance break or excel stage by stage: impression to click, click to...

[Full prompt continues for Pro members.]

Unlock the complete prompt

Pro includes the complete prompt library and every complete workflow.

View Pro options

What you provide

The campaign
The numbers
The goal it had
What the team believes happened

What you receive

The goal verdict: did it hit the number it was accountable for? State plainly. If the goal was fuzzy, say that first, because fuzzy goals make every campaign "a success."
The funnel autopsy: where did performance break or excel stage by stage: impression to click, click to conversion, conversion to pipeline. Identify THE constraint stage, the one...
The narrative check: does the data support what the team believes happened? Where the internal story and the numbers disagree, flag it directly.
The cost truth: real cost per pipeline dollar, including the team hours if I gave them, compared honestly against our other channels
The decisions: three lists:
The one experiment the results suggest for next quarter

Quality checks

Rule: "engagement was strong" is not a finding. Every conclusion needs a number and a comparison point. If the data is too thin to conclude, the finding is "instrument better," and list what to track.