Use a hybrid AI-then-instructor grading workflow with immutable override history¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The system implements grading as a two-stage workflow: "Firstly, AI scores the initial score, and then the teacher confirms whether the score is reasonable". The teacher can overwrite the AI's grade, and both the original and overwritten transactions remain visible in the chain history so scoring can be traced back. Instructors grade manually through the LMS, which calls the blockchain recordGrade function with the teacher's signature instead of the AI's input.

Design Implications¶

Context¶

Requirements¶

• Instructors must hold blockchain identities enabling them to approve grades and initiate certificate issuance through smart contracts

Constraints¶

Target Learners¶

• higher education students
• online course instructors

Target Learning Goals¶

• reliable and auditable assessment of student work

Affordances¶

• Llm Consortium Blockchain Online Education Architecture

Related Strategies¶

• Three-stage hybrid workflow: API batch review, identification of doubtful cases, focused conversational teacher review

Examples¶

-

Key Sources¶

• Fuan Xiao, Jiahui Huang, Jia-Xin Huang, Huali Ren and Lang Li. (2026). Integrating LLM with consortium blockchain for personalized and verifiable online education in higher education. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-026-00618-5