What problem does it solve?
Builds and coordinates the full lifecycle of university assessments—from blueprint design to item creation, integrity auditing, and post-exam analysis—by orchestrating a 7-agent team. This approach reduces misalignment between outcomes, Bloom levels, rubrics, and assessment logistics, while making provenance and iteration traceable across instruments.
Core Features & Use Cases
- End-to-end instrument design: blueprinting, item writing, key generation, and post-exam analytics, all aligned to course outcomes.
- Agent-driven workflow: blueprint_agent, item_writer_agent, answer_key_agent, rubric_designer_agent, project_designer_agent, integrity_auditor_agent, and item_analyst_agent coordinate to produce consistent instruments.
- AI-era integrity focus: built-in integrity audits and a traceable workflow that surfaces risk assessments and redesign options.
- Passport-ready outputs: artifacts such as blueprint, items, key, rubric, and audit reports are produced for downstream use and revision history.
Quick Start
Provide a course outcome set, confirm a blueprint, and trigger item writing and key generation using the 7-agent workflow.
