Customer Feedback Collection
When a support ticket closes, the agent drafts a personalized feedback email with survey links and sends it via Gmail.
customer support teamsops and IT teams
What it does
You get automated, personalized feedback requests from every resolved support ticket right in your Gmail inbox. This workflow pulls data from Google Sheets, uses AI to craft tailored messages with survey links, and centralizes all responses for easy quality tracking while sending alerts to Slack.
Step by step
- Configure a Google Sheets trigger to watch for new rows and filter where the status column equals 'Resolved'.
- Set up a Gmail connection with scopes for sending emails on behalf of the service account.
- Create a Slack webhook endpoint or use the native Slack app integration to post messages to a specific channel.
Where the LLM does the work
- Generate personalized email body text that references specific ticket details and maintains a polite, professional tone.
- Construct dynamic survey links that include unique identifiers for each customer to track response rates accurately.
- Draft concise Slack alert summaries that highlight key metrics or unusual feedback patterns from the collected responses.
Watch out for
Azure OpenAI tokens can accumulate quickly with large datasets, so implement token counting and budget alerts before deployment.
Survey links might break if URL encoding is mishandled, so test link generation with special characters in customer names.
Tools that fit
Azure OpenAI Chat Model LLM Generating personalized email content via AI Agent
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Customer Feedback Collection: When a support ticket closes, the agent drafts a personalized feedback email with survey links and sends it via Gmail. ## Specification - What it does: You get automated, personalized feedback requests from every resolved support ticket right in your Gmail inbox. This workflow pulls data from Google Sheets, uses AI to craft tailored messages with survey links, and centralizes all responses for easy quality tracking while sending alerts to Slack. - Trigger: Run manually (Manual · on demand) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - Google Sheets: Source of ticket data and status filtering - Gmail: Sending personalized feedback request emails - Slack: Alerts and notifications - Azure OpenAI Chat Model: Generating personalized email content via AI Agent ## Known pitfalls, handle each one explicitly in your implementation 1. Azure OpenAI tokens can accumulate quickly with large datasets, so implement token counting and budget alerts before deployment. 2. Survey links might break if URL encoding is mishandled, so test link generation with special characters in customer names. ## Reference implementation https://n8n.io/workflows/8752 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/automated-customer-feedback-collection/ via usecasesforagents.com
Frequently asked questions
Can I use a different Spreadsheet than Google Sheets?
Yes. Google Sheets is only the example spreadsheet in this recipe. The same flow works with Airtable, Baserow and Excel. Swap the spreadsheet connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for support teams drowning in inbound and looking to triage faster, not just harder.
Ops-IT teams triaging their own internal requests get the same pattern, different queue.