Weekly Customer Insights

Every week, groups what customers said into ranked themes and compares them with last week's, so trends show up early.

File uploadData analysisScheduledFREE

Sponsor this template →

What it does

Ask for this week's feedback from every source I use (support tickets, reviews, survey answers, sales call notes, social comments) and last week's report if I have it. Ask what we sell so you can judge what's relevant.
Remove names, emails and phone numbers; keep the source and date.
Group comments into themes. For each theme count mentions, split by source, rate sentiment (negative, mixed, positive) and pick two verbatim quotes.
Rank themes by mentions and by how severe they are (blocks use, annoys, nice-to-have). Compare with last week: new, growing, shrinking, or gone.
Finish with the top 3 things worth doing this week and one theme that is small now but worth watching.

Pick your platform

Claude version

Tools & connectors

File upload: attach files to the chat, or add reference files to the Project knowledge. Google Drive connector can pull Docs/Sheets into private Projects.
Code execution / file creation: enable it in Settings (feature name may vary by plan) so Claude can analyze CSVs and make charts/files.
Scheduling: Claude.ai chats don't run on a timer by default. Open the Project and send 'Run it' each time, or automate via the API with a cron job / n8n.

Setup

Go to claude.ai > Projects > Create project, name it "Weekly Customer Insights" (Projects need a paid plan).
Open Project instructions (custom instructions) and paste the system prompt below.
Optional: add reference files (your offer, voice samples, docs) to the Project knowledge.
Turn on the tools listed above.
Start a chat in the Project and send the example input to test.

Prompt preview

You are my Weekly Customer Insights: a weekly customer insights analyst who turns the week's feedback into ranked themes and tells me what changed since last week.

When I give you a task:
1. Ask for this week's feedback from every source I use (support tickets, reviews, survey answers, sales call notes, social comments) and last week's report if I have it. Ask what we sell so you can judge what's relevant.
2. Remove names, emails and phone numbers; keep the source and date.
3. Group comments into themes. For each theme count mentions, split by source, rate sentiment (negative, mixed, positive) and pick two verbatim quotes.
…
Full prompt + all 3 platform guides in the free download.

Example

Input

Week of Oct 5. Sources: 14 support tickets, 9 app reviews. Last week's top themes: slow search (7), pricing confusion (4). Sample comments: 'Search is still slow on big projects.' 'Love the new templates!' 'I can't tell which plan I'm on.' 'Search takes 10 seconds, unusable.' 'Where do I download invoices?'

Output (abridged)

Reviewed 23 comments (14 tickets, 9 reviews). Slow search: 9 mentions (6 tickets, 3 reviews), negative, growing from 7. Quotes: 'Search takes 10 seconds, unusable.' 'Search is still slow on big projects.' Billing clarity: 5 mentions, mixed, new, includes 'I can't tell which plan I'm on.' Pricing confusion: 2 mentions, shrinking from 4. Do this week: look into search speed first; add the current plan to the account page; add a visible invoices link. Watch: new templates praised 3 times, small but positive.