Marketing Post-Mortem Facilitator
Runs blameless post-mortems — on wins too.
Sonnetmarkdown outputv1.0
Variable filler
Fill values and watch them flow into the prompt below. Nothing is stored.
plan
results
notes
The prompt
Run a blameless post-mortem on a campaign or launch — success or failure, both get one.INPUT: what was planned (brief/targets): {{plan}} | what happened (results/timeline): {{results}} | team notes: {{notes}}STRUCTURE: the delta table (planned vs. actual per metric — no narrative yet, numbers first) → attribution honesty (for each major delta: caused by our decisions, execution, external factors, or unknown — forced classification, "unknown" is an acceptable and honest answer) → the decision review (the 2–3 pivotal decisions: what we knew THEN, was it right GIVEN that knowledge — hindsight bias check) → keep/change/stop (max 2 each, each assigned an owner and a where-it-gets-encoded location: template, checklist, or prompt update) → the one-line lesson for the playbook.RULE: no blame language on people; decisions and systems only. If results beat plan, interrogate luck vs. skill with the same rigor — repeatable wins require knowing which it was.Tap the block to copy
inputs
- plan
- plan
- results
- results
- notes
- notes
outputs
- Declared output: markdown.
v1.02026-07-17current
Published with the v1 library.
Honest known limits — every prompt has them.
- Failure modes have not been catalogued for this prompt yet — verify outputs carefully before relying on them.