Stackby transforms sprawling, unstructured product feedback—app reviews, long user interviews, survey responses, and detailed bug reports—into crisp, actionable product development takeaways by seamlessly integrating advanced intelligence through AI Field Agents.
Here is the step-by-step process to set up an AI-powered product feedback analysis workflow using Stackby's no-code environment.
Step 1: Set Up Your Data Repository
Start with a foundational, relational database structure within Stackby to organize your unstructured feedback.
Create a New Stack: From your Stackby dashboard, start a new "Stack" (database).
Create Table: Create a table to house your source feedback.
"Product Feedback": Store data like Date, User ID, Source (Single Select), a Long Text column for Detailed User Note (the raw feedback), and a Link to a User Story.
Step 2: Add AI-Powered Columns (AI Field Agents)
Integrate intelligence directly into your data tables by adding the specialized AI column type.
Select Column Type: In your data table (e.g., "Product Feedback"), click the + icon to add a new column.
Choose "AI" Field Agent: Select the AI column type from the column properties menu. This is Stackby's AI Field Agent, configured to perform the analysis task.
Name Your Column: Give the column a clear, descriptive name reflecting the output, such as "Feature Theme," "Core User Need," or "Sentiment Flag."
Step 3: Connect Your AI Provider (Bring Your Own Key)
This is the control step where you link your Stackby workspace to your external AI service.
Find Your API Key: Obtain your unique API key from your preferred AI provider e.g., OpenAI, Gemini, Anthropic.
Paste Key into Stackby: When you configure your new AI column, you will be prompted to paste your API key. Once linked, Stackby acts as the conduit, running your prompts against the provider, with all usage and billing managed by that provider.
Step 4: Craft Your Custom AI Prompt
The power of Stackby's AI lies in the flexibility of its prompting. You instruct the AI precisely on what to find and how to present it for prioritization.
Target Table | Output Column | Example Prompt |
Product Feedback | English Translation | Translate [ Review Text] into English. Focus on accurately conveying the sentiment and ideas expressed in the review. State which language you have translated from in parenthesis after the translation. |
Product Feedback | Category | Assign a category to the review based on the contents of Review Text ]. Your options are: User Experience (UX) Only ever use one category. If the review does not obviously fit into any of these categories, assign "Other" instead. Don't add any other text except the category. |
Reference Template: Product Feedback Analysis Template
