ClassLens VS FriendlyData

• Draft grades from your rubric or assignment instructions
  If the teacher attached a rubric, ClassLens grades against it. If not, it works from the assignment description. Either way it drafts a score and written feedback for each submission. Before grading, teachers set strictness, feedback style and how late work is handled.
• Teacher review before anything is returned
  Grades go to Google Classroom as drafts, or to a review dashboard where the teacher checks each result and releases them all at once. ClassLens never returns grades to students by itself.
• Knowledge Gap Reports
  After grading, ClassLens shows which concepts the class missed most, so teachers know what to reteach. A sample report built on synthetic data is at classlens.com/demo, no sign-in needed.
• Works with what students turn in
  Teachers sign in with Google and pick assignments from Google Classroom. ClassLens grades documents, PDFs, images, and uploaded audio and video. Linked videos aren't supported, so the file has to be attached.
• Security and privacy
  Google OAuth verified, including the restricted Google Drive scope. CASA Tier 2 security assessment complete. SOC 2 Type I attested. Evolved Academics is also a CISA Secure by Design Pledge signatory. Student work is processed on Google Vertex AI with Zero Data Retention enrolled at the project level (no prompt logging, no training use).

• Ease of Use
  FriendlyData allows users to interact with databases using natural language queries, which makes it accessible for non-technical users who are not familiar with complex database query languages.
• Time-Saving
  By enabling natural language processing, FriendlyData reduces the time it takes for users to get the information they need, facilitating quicker decision-making processes.
• Integration
  FriendlyData can be integrated with various platforms and services, making it versatile for different business needs.

Possible disadvantages

• Complex Queries Limitation
  While FriendlyData is useful for simple queries, it may struggle to accurately interpret and execute more complex queries, limiting its effectiveness for advanced data analysis.
• Language Ambiguity
  Natural language processing might not always accurately interpret user queries, especially if the input is ambiguous or lacks specificity.
• Dependency on Vendor
  Relying on third-party services like FriendlyData introduces dependency on the vendor for maintenance, updates, and support, which could pose risks if the service changes or is discontinued.