Convert product reviews into a weekly action digest
Collect new product reviews and surface recurring problems, valued features, and requests that product owners can investigate.
How this works
Collect new product reviews and surface recurring problems, valued features, and requests that product owners can investigate. Use this to summarize new product reviews into themes that product owners can investigate. The digest should preserve sample size, duplicate handling and the difference between customer sentiment and verified technical problems.
Collect a dated review snapshot, calculate rating statistics with explicit denominators, and group praise, problems and requests. Retain representative evidence and translation caveats. Connect findings to owners and product metrics without treating a review sample as the full customer population.
Before you start
Review sources
Choose permitted stores, forms or review platforms and a fixed window.
Product taxonomy
Obtain feature areas and routing owners.
Rating rules
Define averaging, edited reviews and duplicate treatment.
Prepare the inputs
- reviews
- Required
ID, date, rating, text, locale and product version
Retain original text and distinguish new from edited reviews.
- reporting_window
- Required
start, end and timezone
Use one consistent cutoff.
- routing_map
- Required
topic and responsible product area
Unknown topics remain unassigned.
- product_metrics
- Required
optional comparable operational indicators
Do not infer causation from coincident trends.
Implementation, step by step
Collect and reconcile
- Import reviews and record source coverage and unavailable channels.
- Deduplicate repeated records and preserve edits as versions.
Checkpoint: The weekly sample is defined.
Calculate rating measures
- Compute counts, average and distribution using deterministic arithmetic.
- Show the denominator and avoid comparing incompatible rating scales.
Checkpoint: The numerical summary is reproducible.
Group qualitative evidence
- Classify praise, problems and feature requests by underlying topic.
- Retain representative and contradictory examples, checking translations where needed.
Checkpoint: Themes remain grounded in original reviews.
Route investigation items
- Connect recurring or severe issues to relevant product owners.
- Separate customer-reported symptoms from verified root causes.
Checkpoint: The digest has useful next questions.
Review and publish status
- Check counts, examples and prior follow-ups before preparing the final draft.
- Track owner responses without automatically creating roadmap commitments.
Checkpoint: The weekly brief includes coverage and open actions.
Decisions along the way
One user edits a review repeatedly
Count according to the approved rule and retain the latest versus prior text.
Translation is uncertain
Keep the original and flag the theme for review.
A severe issue appears once
Surface it with its limited evidence rather than hide it behind frequency.
What you will produce
weekly-review-digest.md
MarkdownAn evidence-linked product review brief.
Include: rating_summary · praise · problems · requests · evidence · coverage
review-followups.csv
CSVA queue for investigation and follow-up.
Include: theme · review_ids · owner · question · status
Check the result
- Recalculate average ratings and denominators.
- Verify representative examples match their themes.
- Check duplicates and edited reviews are handled consistently.
- Confirm no symptom is labeled a proven technical cause without evidence.
When something goes wrong
Source export is incomplete
State missing coverage and avoid a complete-week claim.
Rating scale changes
Separate the series or normalize only with an explicit rule.
Theme classifier merges unrelated complaints
Split the cluster and recount unique records.
A worked example
SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT
Request
Synthetic: summarize five new reviews.
Inputs
Ratings are 5, 4, 4, 2 and 1. Two low-rating reviews describe login trouble, but one is a duplicate export of the same review ID.
Expected result
Synthetic result: deduplicate first, calculate the rating from the remaining unique records and report one or two login observations according to actual IDs. Do not average five rows blindly.
Run a small pilot
Start small
Produce two weekly digests for one product and a fixed source set.
Record the baseline
Record analysis time and theme or counting corrections.
Agree success criteria
Agree rating accuracy and evidence quality before routine distribution.
Stop or revise
Stop trend claims when source coverage changes without a comparable basis.
Keep the scope clear
- Review sentiment does not establish customer-wide prevalence or root cause.
- The digest informs product investigation rather than automatically setting priorities.
Check before using
Check sample size, duplicates, translation, and rating calculation. Review sentiment alone cannot establish prevalence or technical root cause.
Business activities
- Coordinate meetings and follow-ups
- Plan products and business changes
FROM A RECIPE TO YOUR WORKFLOW
Bring the company context together.
This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.
For this recipe: Permitted review sources · Reporting window · Product ownership map
Start with one recurring task, agree which sources to use, and review the first result with your team.
Discuss this workflow