Observed arrival · 2026-08-24
evaluchat: measuring learning with AI in the room
An open-source workspace and research catalogue for testing how AI changes education, assessment, and evidence of learning.
Field notes
The project separates three capabilities that are often collapsed into one assessment: producing independently, understanding the underlying work, and evaluating or correcting AI output. Its proposed research sequence links a question to a method, workspace activity, public record, and later claim or replication. The workspace supports Markdown documents with Mermaid and LaTeX rendering, optional AI assistance, printing, and PDF output, while the site states that AI can be turned off.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue