Writing rubrics for Reasonate
The rubric is the most important thing you'll write. It tells the AI what dimensions to probe — and ultimately determines how your students are scored.
The core principle
A Reasonate rubric is not a list of acceptable answers. It's a list of what a student must demonstrate understanding of — the concepts, mechanisms, distinctions, and reasoning chains they need to articulate to prove they actually get it.
Write your rubric the way you'd brief a TA who's going to verbally examine a student: “make sure they explain X, get them to articulate Y, watch for the common mistake of Z.”
What makes a good rubric
- Specific concepts, mechanisms, or causal chains the student must articulate
- Common misconceptions to probe for (it's worth catching these explicitly)
- Distinctions the student must make (X vs Y) where confusion is common
- The kind of example or case study they should be able to walk through
- Vague terms like 'good understanding' or 'demonstrates mastery'
- Lists of acceptable answer phrasings (the AI doesn't grade phrasing)
- Rules about length, format, or grammar
- Pure factual recall ('list the 5 steps') — Reasonate grades reasoning, not memory
Strong example vs. weak example
“Student should understand photosynthesis well and explain the main concepts clearly.”
Why: Doesn't tell the AI what specifically to probe. Every learner will get probed differently, which makes scores inconsistent.
“The learner must explain: (1) the inputs (CO2, water, light) and outputs (glucose, O2); (2) the two stages — light-dependent reactions in the thylakoid, and the Calvin cycle in the stroma; (3) the role of ATP and NADPH as energy carriers between stages; (4) why photosynthesis is critical to the global oxygen and carbon cycles. Probe whether they understand mechanism, not just memorize inputs/outputs. Watch for: confusing 'making food from sunlight' as a complete answer — push for HOW.”
Why: Tells the AI exactly which concepts to test, gives specific things to challenge, and flags a common misconception. Will produce consistent scores.
The 5 scoring dimensions
Behind the scenes, Reasonate scores every conversation across 5 dimensions, each 0-20:
Your rubric primarily drives Coverage (what must be touched) and Depth (what level of explanation counts as deep). The other three are universal.
Templates you can copy
The learner must explain: (1) the inputs and outputs; (2) the key stages and what happens in each; (3) the mechanism by which inputs become outputs; (4) WHERE this happens (cellular, physical, conceptual location); (5) at least one concrete example. Push for mechanism — surface answers (“X makes Y”) should get followed up with “but HOW?”
The learner must explain: (1) the main causal factors; (2) how those factors link together to produce the outcome (the chain, not just the list); (3) why this outcome happened HERE and THEN — what made the conditions ripe; (4) at least one counterfactual (“what would have prevented this?”); (5) the most common misconception about this topic.
The learner must explain: (1) the formal definition of each concept; (2) where the two concepts overlap (and why people confuse them); (3) the precise dividing line; (4) a concrete example of each that the other does NOT cover; (5) why the distinction matters in practice.
The learner must explain: (1) what each term in the formula represents physically/conceptually; (2) the derivation or intuition (not just the formula); (3) when the formula applies vs. when it breaks; (4) a worked example; (5) the most common error students make using this formula.
A rubric-writing checklist
- Does the rubric list 3-6 specific things the learner must articulate?
- Does it focus on mechanism / reasoning, not just facts?
- Does it flag a common misconception worth probing?
- Could the AI use this rubric to ask follow-up questions without you in the room?
- Would two different graders following this rubric arrive at similar scores?