How can AI help Colorado evaluators write teacher evaluations under the State Model?
How can AI help Colorado evaluators write teacher evaluations under the State Model?
Colorado evaluates teachers under the framework built by Senate Bill 10-191, the Great Teachers and Leaders Act, and the honest answer about AI follows the shape of that system. A Colorado teacher's evaluation has two portions: professional practice, measured through four Teacher Quality Standards, and Measures of Student Learning. AI can genuinely help with the first — mapping observation evidence to the right element of the Quality Standards and drafting feedback in the state rubric's own language. What it can't do is measure student learning, combine the two portions into a Final Effectiveness Rating, or decide which system your district adopted. This post walks through where AI helps with the Colorado State Model, where it doesn't, and what to look for.
What the Colorado State Model actually is
In 2010, Senate Bill 10-191 overhauled how Colorado supports and evaluates educators, tying ratings in part to professional practice and in part to student learning, and making non-probationary status a function of demonstrated effectiveness rather than years served. To help districts implement it, the Colorado Department of Education (CDE) built the State Model Evaluation System — a rubric and process districts may adopt.
The State Model is an option, not a mandate. Districts may use it or adopt their own evaluation system, provided the local plan meets the State Board's rules and is built on the Colorado Teacher Quality Standards. Either way, the Quality Standards are the common backbone, which is what makes a Quality-Standards-based tool useful statewide.
The four Teacher Quality Standards
The professional-practice portion of a Colorado evaluation is organized into four Quality Standards, each measured through the state's Revised Rubric for Evaluating Colorado Teachers using defined elements:
Quality Standard I — Content Knowledge. Teachers demonstrate mastery of, and pedagogical expertise in, the content they teach, aligned to the Colorado Academic Standards.
Quality Standard II — Learning Environment. Teachers establish a safe, inclusive, and respectful learning environment for a diverse population of students.
Quality Standard III — Facilitation of Learning. Teachers plan and deliver effective instruction, facilitating learning and using assessment to guide it.
Quality Standard IV — Professionalism. Teachers demonstrate professionalism through ethical conduct, reflection, collaboration, and continuous professional growth.
Each standard breaks down into elements, and it's at the element level that an evaluator gathers evidence and settles on a rating. That granularity is real work: a full evaluation touches dozens of points, each needing evidence.
The part that changed: the 70/30 split
If you're working from older Colorado guidance, this is the number to update. For roughly a decade after SB 191, a Colorado teacher's evaluation was split evenly — 50% professional practice, 50% Measures of Student Learning. That is no longer the case.
Beginning in the 2023-24 school year, under SB 22-070, the split shifted to emphasize professional practice: 70% of the Final Effectiveness Rating now comes from the four Quality Standards, and 30% comes from Measures of Student Learning/Outcomes (MSLs/MSOs). CDE also rebuilt the scoring model to a 1,000-point scale to reflect the change. Some CDE materials still describe the old "half and half" arrangement, so it's worth confirming you're looking at the current 70/30 framing.
For an evaluator, the practical effect is that professional practice — the observation-based portion — now carries the clear majority of the rating. That raises the stakes on getting the observation documentation right.
How Measures of Student Learning work
The remaining 30% comes from Measures of Student Learning, and Colorado is deliberate about how they're built. Evaluations must use multiple measures, not a single assessment. A teacher must have a collective or shared attribution measure and at least one individual attribution measure; where a teacher's subject is covered by the statewide summative assessment or the Colorado Growth Model, that result is used as one of the measures. This is a district-level scoring exercise, distinct from the observation write-up.
After the observation: where the work piles up
The observation itself is familiar work for an experienced Colorado evaluator. The write-up that follows is where the hours go: taking fragmentary observation notes and organizing them as evidence against the right elements of the Quality Standards, settling on a defensible rating for each, and drafting feedback a teacher can act on — then doing it again across a caseload, on Colorado's annual cycle. With professional practice now at 70%, this documentation is most of the rating.
Where AI helps with the Colorado write-up
The strongest fit between current AI and Colorado's system is that professional-practice 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 reasoning to each other" and a sentence tied to Quality Standard III on facilitating learning. Second, it maps evidence to the right element, including evidence that supports more than one — a well-run discussion can speak to both the learning environment and facilitation of learning. Third, it holds consistency across a caseload, so the same quality of evidence lands in similar territory from teacher to teacher rather than drifting with the hour of the night.
For Colorado specifically, the value is keeping the write-up in the Quality Standards' own element language and rating levels, so it's ready to carry into your district's scoring process 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 Colorado built the system.
AI cannot measure student learning or calculate your Final Effectiveness Rating. Tools like EvalScribe draft the professional-practice piece — the 70%. The Measures of Student Learning and the combination of both portions into the final rating are handled in your district's scoring process.
AI cannot decide which system your district uses. Because Colorado allows the State Model or an approved local plan, the specific rubric is a local fact to confirm.
AI cannot supply an evaluator's professional and local judgment — what the evidence really shows, how a teacher's year unfolded, how a rating fits the context. That stays with the evaluator, who remains the last set of eyes on every rating and comment.
And general-purpose AI in particular has no built-in understanding of the Colorado rubric. Paste notes into a consumer chatbot and it will invent standards and elements, reach for the wrong rating levels, and sometimes assume the old 50/50 weighting. For a document tied to non-probationary status and employment decisions, those errors are the kind that surface at the worst possible moment.
What to look for in an AI tool for the Colorado State Model
A few questions worth asking before committing a tool to this work.
Does the tool actually know the four Quality Standards and their elements, or does it produce generic "good teaching" language?
Does it draft toward Colorado's four rating levels — Highly Effective, Effective, Partially Effective, Ineffective — using the rubric's own criteria?
Does it stay in its lane, drafting professional practice and leaving Measures of Student Learning and the final rating to your district's scoring process?
Where does your observation data live? Is it stored on the vendor's servers, or used to train models?
How EvalScribe handles the Colorado State Model
EvalScribe is built around the four Teacher Quality Standards and their elements. An evaluator captures notes by typing, dictating, or photographing handwriting (Smart Scan OCR converts it to text), EvalScribe maps that evidence to the element it supports, and drafts a rating and evidence-anchored feedback for each — using the state rubric's own language across the four levels: Highly Effective, Effective, Partially Effective, Ineffective. Every rating and comment is fully editable before export, and the evidence stays traceable to the note it came from.
Two scope notes, because Colorado's structure calls for them. First, EvalScribe drafts the professional-practice piece — the four Quality Standards, which make up 70% of the Final Effectiveness Rating. The Measures of Student Learning/Outcomes (the other 30%) and the combination of both portions into the final rating are handled in your district's scoring process, not the app. Second, because Colorado's State Model is an option and districts may use an approved local plan, EvalScribe is built on the Quality Standards the state rubric shares; confirm your district's adopted system.
Beta testers report saving 30 to 60 minutes per evaluation versus writing the documentation by hand. Across a full caseload on Colorado's annual cycle, that adds up to dozens of hours back — hours that can go to the feedback conversation the ratings are meant to support. More detail on the Colorado workflow is available at evalscribe.com/colorado.
Frequently asked questions about the Colorado State Model and AI
Does EvalScribe support the Colorado State Model? Yes. It's built around the four Teacher Quality Standards — Content Knowledge, Learning Environment, Facilitation of Learning, and Professionalism — and drafts ratings and feedback across the four levels (Highly Effective, Effective, Partially Effective, Ineffective).
How much of a Colorado evaluation is professional practice? Since 2023-24, under SB 22-070, professional practice is 70% of the Final Effectiveness Rating and Measures of Student Learning are 30% — a change from the earlier 50/50 split.
Does EvalScribe calculate my Final Effectiveness Rating? No. It drafts the professional-practice piece; Measures of Student Learning and the final combination happen in your district's scoring process.
Can I use it if my district uses its own system? Often, yes. Colorado allows the State Model or an approved local plan, and EvalScribe is built on the Colorado Teacher Quality Standards both share. Confirm your district's adopted system.
Does AI replace evaluator judgment? No. The observation, the ratings, and the professional judgment are yours. AI translates your judgment into standards-aligned documentation.
If you're evaluating teachers in Colorado, see how EvalScribe drafts in the four Quality Standards and rating levels at evalscribe.com/colorado. Questions, or a school or district license? Reach the team at [email protected].
References
Colorado Department of Education, Educator Evaluation Requirements (the current 70/30 professional-practice/MSL split)
Colorado Department of Education, State Model Evaluation System for Teachers (the four Quality Standards and revised rubric)
Colorado Department of Education, Senate Bill 10-191 Legislative Overview (the Great Teachers and Leaders Act)
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 Colorado Department of Education's Educator Effectiveness resources and Senate Bill 10-191.
Last updated on July 28, 2026.
