Sentiment Analytics Visualizer
Fetches customer reviews from a sheet, classifies sentiment with GPT-4o-mini, and emails a doughnut chart summary to the team.
customer support teamsops and IT teams
What it does
You get instant clarity on customer feedback as this agent pulls reviews from your Google Sheet, classifies each one with GPT-4o-mini, and updates the sheet with results. It then generates a visual doughnut chart summary and emails it to your team so everyone stays informed without manual tracking.
Step by step
- Configure the Google Sheets trigger to poll for new rows or changes in a specific range.
- Set up the code node to parse the LLM response and increment counters for Positive, Neutral, and Negative categories.
- Construct the QuickChart URL with the doughnut chart configuration including labels and data arrays.
Where the LLM does the work
- Prompt the OpenAI model with the review text and a strict instruction to return only 'Positive', 'Neutral', or 'Negative'.
- Handle cases where the LLM returns unexpected formats by adding system instructions for consistent output.
- Refine the prompt if reviews contain mixed sentiments that require nuanced classification logic.
Watch out for
Inconsistent LLM outputs will break the tallying code, enforce strict JSON or string-only responses in your prompt.
QuickChart URLs have length restrictions for large datasets, limit the chart data to aggregated counts rather than individual reviews.
Gmail attachments may exceed size limits if not handled correctly, ensure you are sending a URL link to the chart instead of embedding a large image file.
Tools that fit
OpenAI Chat Model LLM Classify review sentiment
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 Sentiment Analytics Visualizer: Fetches customer reviews from a sheet, classifies sentiment with GPT-4o-mini, and emails a doughnut chart summary to the team. ## Specification - What it does: You get instant clarity on customer feedback as this agent pulls reviews from your Google Sheet, classifies each one with GPT-4o-mini, and updates the sheet with results. It then generates a visual doughnut chart summary and emails it to your team so everyone stays informed without manual tracking. - Trigger: Run manually (Manual · on demand) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - Google Sheets: Store and update customer reviews - OpenAI Chat Model: Classify review sentiment - QuickChart: Generate doughnut chart image - Gmail: Email the sentiment chart to recipients ## Known pitfalls, handle each one explicitly in your implementation 1. Inconsistent LLM outputs will break the tallying code, enforce strict JSON or string-only responses in your prompt. 2. QuickChart URLs have length restrictions for large datasets, limit the chart data to aggregated counts rather than individual reviews. 3. Gmail attachments may exceed size limits if not handled correctly, ensure you are sending a URL link to the chart instead of embedding a large image file. ## Reference implementation https://n8n.io/workflows/5204 (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/sentiment-analytics-visualizer/ 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.