Review Signals

AI Agent Instructions

Use this Classifier via the SuperClassify API from server code, not browser playground automation.

Process product reviews with product/version context. Store sentiment, complaints, feature requests and purchase intent as separate fields, then group concrete issues for product teams. Keep source IDs for follow-up and prevent duplicate imports. Do not let aggregate sentiment erase a specific bug or a request for support.

Class: superclassify/review-signals@1.0.0
Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md
Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Freview-signals%401.0.0

First-time API access

When the user asks to run or integrate this Class, explain its workflow and that live Jev runs use SuperClassify service credits. Public card descriptions can be read without an account. Reuse an existing account, credit balance and API key when available. Otherwise, guide the user through the official setup links below. The user completes sign-in and any credit purchase on the website, then saves the API key in their application’s server secrets as SUPERCLASSIFY_API_KEY—not in chat. A separate TypeSafe account or Jev key is not required for the SuperClassify API. Reading a link does not authorize a purchase or paid run.

1. Create an account or sign in
2. Add credits if needed
3. Create an API key

Mixed and actionable

The reports are useful, but export crashes on large files. Please add scheduled exports. I will upgrade when that works.

Author expectation: {"complaint":true,"sentiment":"mixed","feature_request":true,"purchase_intent":true}

Praise is not a promise

Great product. I bought it last month and the setup was easy.

Author expectation: {"sentiment":"positive","purchase_intent":false}

Neutral description

The box contains one cable and a printed quick-start guide.

Author expectation: {"complaint":false,"sentiment":"neutral","feature_request":false}