How can AI help Ohio evaluators write OTES 2.0 teacher evaluations?
How can AI help Ohio evaluators write OTES 2.0 teacher evaluations?
Ohio evaluates every teacher on the same statewide system, OTES 2.0, and most of what an evaluator documents is the performance rubric — six domains, each scored from classroom observation. That's where AI can genuinely help: drafting the observation write-up, mapping evidence to the right domain, and putting it in the rubric's own language. What it can't do is supply the high-quality student data or produce the Final Holistic Rating. This post walks through where AI helps with OTES 2.0, where it doesn't, and what to look for.
What OTES 2.0 actually is
The Ohio Teacher Evaluation System 2.0 (OTES 2.0) is the statewide model for evaluating teachers, aligned to the Ohio Standards for the Teaching Profession and adopted under Ohio Revised Code. Oversight sits with the Ohio State Board of Education. It is explicitly a professional-growth model, meant to be collaborative, ongoing, and supportive rather than a compliance exercise.
A teacher's Final Holistic Rating is not the observation alone. It combines two things: the Teacher Performance Evaluation Rubric, scored from observations and supporting evidence, and high-quality student data. Both feed the final rating.
The six rubric domains
The performance rubric is used holistically across six domains, grouped by the part of practice they describe:
Focus for Learning (planning) — use of high-quality student data, connections to prior and future learning, and alignment to Ohio's Learning Standards and district priorities.
Knowledge of Students (planning) — planning instruction for the whole child, using students' development, backgrounds, strengths, and social-emotional needs.
Lesson Delivery (instruction) — communication with students, monitoring student understanding, and student-centered learning.
Classroom Environment (instruction) — routines and procedures, and a climate of fairness, respect, and cultural competency.
Assessment of Student Learning (instruction) — use of assessments throughout instruction and clear evidence of student learning.
Professional Responsibilities (professionalism) — communication and collaboration with families and colleagues, district policies and responsibilities, and professional learning.
The four ratings
Each domain is scored on a four-level scale: Ineffective, Developing, Skilled, Accomplished. Skilled is the expected professional standard — effective, consistent practice appropriate for the students and the content. Accomplished sits above it and reflects exemplary practice with strong student ownership of learning. The distinctions between adjacent levels are specific, which is what makes the write-up demanding.
High-quality student data and the holistic rating
Alongside the rubric, OTES 2.0 requires at least two measures of high-quality student data (HQSD) that provide evidence of student learning attributable to the teacher. The Final Holistic Rating combines the performance evidence with HQSD. HQSD is a district and state matter, calculated outside any observation write-up.
The observation cadence
A full OTES 2.0 evaluation requires at least two formal observations of at least 30 minutes each and at least two classroom walkthroughs, conducted by a credentialed evaluator. Evaluations are completed by May 1, and a written report is provided to the teacher by May 10. Districts may move teachers rated Skilled or Accomplished to a less-frequent cycle — every two or three years — provided the teacher is on a Professional Growth Plan and making progress.
That still adds up to real volume, and each observation needs a written record tied back to the six domains.
After the observation: where the work piles up
The observation itself is familiar work for an experienced Ohio evaluator. The write-up that follows is where the hours go: taking fragmentary notes and organizing them as evidence against the right domain, settling on a defensible level for each, and drafting feedback a teacher can act on — across every observation the cadence requires, and in time for the May 1 deadline.
Where AI helps with the OTES 2.0 write-up
The strongest fit between current AI and Ohio's system is that rubric-based documentation.
AI handles three parts of it reliably. First, it turns fragmentary notes into coherent, evidence-anchored prose in the rubric's language — the difference between "kids explained their thinking to each other" and a sentence tied to a Lesson Delivery component. Second, it maps evidence to the right domain, including evidence that supports more than one. Third, it holds consistency across a caseload, so the same quality of evidence lands in similar territory from teacher to teacher.
For Ohio specifically, the value is drafting in the rubric's own language and toward the four levels, so the write-up is ready to inform the performance rating rather than something you have to translate first.
Where AI doesn't help — and what stays with the evaluator
The honest scope follows from how OTES 2.0 is built.
AI cannot supply high-quality student data or produce the Final Holistic Rating. HQSD is district and state data, and the holistic rating combines it with the performance evidence under the framework's rules — not something a drafting tool decides.
AI cannot supply an evaluator's professional judgment — what the evidence really shows, how a lesson fit a longer arc, how a rating fits the teacher's year. That stays with the evaluator, who remains the last set of eyes on every rating and comment.
And general-purpose AI has no built-in understanding of the OTES 2.0 rubric. Paste notes into a consumer chatbot and it will invent domains, blur the rubric together with student data, and hand out Accomplished freely. For a statewide system with defined levels and a credentialed-evaluator process, those errors surface at the worst possible moment.
What to look for in an AI tool for Ohio
A few questions worth asking before committing a tool to this work.
Does the tool actually know the six OTES 2.0 domains and their components, or does it produce generic "good teaching" language?
Does it draft toward Ohio's four levels — and hold Skilled as the professional standard rather than inflating to Accomplished?
Does it stay in its lane, drafting the performance rubric and leaving HQSD and the Final Holistic Rating to the district?
Where does your observation data live? Is it stored on the vendor's servers, or used to train models?
How EvalScribe handles OTES 2.0
EvalScribe is built around all six domains of the OTES 2.0 Teacher Performance Evaluation Rubric. An evaluator captures notes by typing, dictating, or photographing handwriting (Smart Scan OCR converts it to text), EvalScribe maps that evidence to the domain and component it supports, and drafts a rating and evidence-anchored feedback for each — using the rubric's own language across the four levels. Every rating and comment is fully editable before you finalize it, and the evidence stays traceable to the note it came from, ready to inform the performance rating.
Two scope notes, because OTES 2.0 calls for them. First, EvalScribe drafts the observation-based performance rubric. High-quality student data and the Final Holistic Rating are determined by the district under the OTES 2.0 framework, not the app. Second, EvalScribe uses the OTES 2.0 rubric as adopted under Ohio Revised Code and overseen by the Ohio State Board of Education.
Beta testers report saving 30 to 60 minutes per evaluation versus writing the documentation by hand. Across the observation cadence OTES 2.0 requires, that adds up to dozens of hours back — hours that can go to the coaching conversation the growth model is built to support. More detail on the Ohio workflow is available at evalscribe.com/ohio.
Frequently asked questions about OTES 2.0 and AI
Does EvalScribe support OTES 2.0? Yes, for the observation-based component — all six domains of the Teacher Performance Evaluation Rubric, with the four rating levels.
How many observations does Ohio require? At least two formal observations of at least 30 minutes each and at least two classroom walkthroughs, by a credentialed evaluator, completed by May 1.
What is HQSD? At least two measures of high-quality student data providing evidence of student learning attributable to the teacher — combined with the rubric to produce the Final Holistic Rating.
What are the rating levels? Ineffective, Developing, Skilled, Accomplished. Skilled is the expected professional standard.
Does EvalScribe produce the Final Holistic Rating? No. It drafts the performance-rubric write-up; HQSD and the holistic rating stay with the district.
If you're evaluating teachers in Ohio, see how EvalScribe drafts across the OTES 2.0 rubric at evalscribe.com/ohio. Questions, or a school or district license? Reach the team at [email protected].
References
Ohio State Board of Education, Educator Evaluations (the OTES 2.0 framework, model, and Teacher Performance Evaluation Rubric)
Ohio Teacher Evaluation System 2.0 Framework (aligned to the Ohio Standards for the Teaching Profession; Final Holistic Rating combining the performance rubric and high-quality student data)
Ohio Teacher Evaluation System 2.0 Model (observation requirements — two formal observations and two walkthroughs — the four rating levels, and the completion timeline)
Related articles
Page maintained by Anthony D. Neely, Ph.D. — practicing K-12 educator with nearly 20 years in the classroom, 2025–2026 Walker County Distinguished Teacher of the Year, and co-founder of EvalScribe. Framework details verified against the Ohio State Board of Education's OTES 2.0 framework, model, and rubric.
Last updated on August 6, 2026.
