How can AI help Maryland evaluators write teacher evaluations?
How can AI help Maryland evaluators write teacher evaluations?
Maryland evaluates teachers differently from most states, and the difference shapes where AI fits. There is no single statewide rubric. Instead, each district builds its own evaluation model within state parameters, and those parameters are anchored by the four Danielson professional-practice domains plus a student-growth component. AI can genuinely help with the professional-practice half — mapping observation evidence to the right Danielson component and drafting feedback in the framework's own language. What it can't do is measure student growth, set a teacher's place on the Blueprint career ladder, or combine everything into an overall rating. This post walks through where AI helps with Maryland evaluations, where it doesn't, and what to look for.
What Maryland's evaluation system actually is
Maryland is a local-control state. Under the state regulation for teacher evaluation, COMAR 13A.07.09, each local education agency develops its own evaluation model, negotiated with its bargaining unit and approved within state parameters. A district may design its own system or adopt a state-developed one, but the design decisions — the exact rating scale, the SLO process, the weighting details — happen locally.
What the state parameters fix is the shape. A teacher's evaluation must include at least five components: the four professional-practice domains, and student growth. The four professional-practice domains are the Danielson domains — planning and preparation, classroom environment, instruction, and professional responsibility. That shared foundation is what makes a Danielson-based tool useful across Maryland even though no two district models are identical.
The four professional-practice domains
The observation half of a Maryland evaluation is measured against Danielson's four domains:
Planning and Preparation. Knowledge of content, students, and resources, and coherent instructional design and assessment planning. The work before students arrive.
Classroom Environment. A culture of respect and rapport, clear expectations, managed routines, and a physical space that supports learning.
Instruction. Clear communication, strong questioning and discussion, engaging students in the work of learning, and using assessment to adjust in the moment.
Professional Responsibility. Reflection on practice, accurate record-keeping, communication with families, professional growth, and contribution to the school community.
Each is described across levels of performance, and the district's rating scale determines how those levels roll up.
The other half: student growth and SLOs
Maryland's state model weights the two halves equally — professional practice and student growth each count for 50%. Student Learning Objectives, or SLOs, are the predominant measure of student growth. A teacher typically develops two to four SLOs, each weighted equally within the growth component, informed by a review of students' baseline data. Teachers in assessed subjects and grades develop at least one SLO informed by the Maryland College and Career Ready Standards.
Because each district runs its own model, the exact weighting and the SLO process vary from one system to the next. The 50/50 split is the state model standard; your district's agreement sets the specifics.
The Blueprint career ladder, in brief
The other current piece is the Blueprint for Maryland's Future, which is reshaping the profession around a teacher career ladder with multiple levels. Districts are aligning their evaluation systems to the career ladder, and an evaluation system used with the ladder must meet specific requirements in state law — including pre- and post-observation conferences, an assessment of the evaluator's competency, and Peer Assistance and Review (PAR).
For an evaluator, the practical effect is more structure around observation and feedback, not a replacement of the Danielson-based professional-practice framework. The observation write-up remains at the center of it all.
After the observation: where the work piles up
The observation itself is familiar work for an experienced Maryland evaluator. The write-up that follows is where the hours go: taking fragmentary observation notes and organizing them as evidence against the right Danielson components, settling on a defensible level for each, and drafting feedback a teacher can act on — then doing it again across a caseload, and, under the Blueprint, within a more structured conference-and-review cycle.
Where AI helps with the Maryland write-up
The strongest fit between current AI and Maryland'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 framework's language — the difference between "kids explained their reasoning to each other" and a sentence tied to the instruction domain. Second, it maps evidence to the right component, including evidence that supports more than one — a well-run discussion can speak to both instruction and classroom environment. 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 Maryland specifically, the value is drafting in the Danielson framework's own component language and toward your district's rating levels, so the write-up is ready for your local model and the Blueprint's conference cycle 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 Maryland built the system.
AI cannot measure student growth or calculate the overall rating. Tools like EvalScribe draft the professional-practice half — the Danielson domains. The 50% student-growth component (SLOs) and the combination of both halves into the overall rating are handled in your district's process.
AI cannot administer the career ladder or PAR. Where a teacher sits on the Blueprint career ladder, and how peer assistance and review are structured, are district decisions, not drafting tasks.
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. Maryland reinforces this by requiring observers to be trained and, under the career ladder, by requiring an assessment of the evaluator's competency.
And general-purpose AI in particular has no built-in understanding of how Maryland works. Paste notes into a consumer chatbot and it will invent components, assume a single statewide rubric that doesn't exist, and reach for rating labels your district may not use. For a document tied to employment and the career ladder, those errors are the kind that surface at the worst possible moment.
What to look for in an AI tool for Maryland
A few questions worth asking before committing a tool to this work.
Does the tool actually know the four Danielson domains and their components, or does it produce generic "good teaching" language?
Does it draft toward your district's rating scale — at minimum Highly Effective, Effective, Ineffective — rather than a one-size gradient?
Does it respect Maryland's local control, adapting to your district's model rather than assuming a single statewide rubric?
Does it stay in its lane, drafting professional practice and leaving SLOs, the overall rating, and career-ladder placement to your district's process?
Where does your observation data live? Is it stored on the vendor's servers, or used to train models?
How EvalScribe handles Maryland evaluations
EvalScribe is built around the four Danielson domains at the heart of every Maryland model. An evaluator captures notes by typing, dictating, or photographing handwriting (Smart Scan OCR converts it to text), EvalScribe maps that evidence to the component it supports, and drafts a rating and evidence-anchored feedback for each — using the framework's own language and drafting toward your district's rating scale. Every rating and comment is fully editable before you finalize it, and the evidence stays traceable to the note it came from.
Two scope notes, because Maryland's structure calls for them. First, EvalScribe drafts the professional-practice half — the Danielson domains, the observation portion of the rating. The student-growth component (SLOs) and the combination of both halves into the overall rating are handled in your district's process, not the app. Second, because each district develops its own model, EvalScribe is built around the Danielson domains every Maryland model shares; confirm your district's adopted model and rating scale.
Beta testers report saving 30 to 60 minutes per evaluation versus writing the documentation by hand. Across a full caseload — and the added structure the Blueprint brings to observation and feedback — that adds up to dozens of hours back, hours that can go to the conversation the ratings are meant to support. More detail on the Maryland workflow is available at evalscribe.com/maryland.
Frequently asked questions about Maryland evaluations and AI
What evaluation model does Maryland use? There isn't one statewide rubric. Under COMAR 13A.07.09, each district builds its own model on the four Danielson professional-practice domains plus student growth. EvalScribe is built around those shared domains.
How much of a Maryland evaluation is student growth? In the state model, professional practice and student growth are weighted equally — each 50% — with SLOs the predominant growth measure. Exact weighting is set by your district.
What are the Maryland rating levels? State regulation requires at least Highly Effective, Effective, and Ineffective; some districts add intermediate levels.
Does EvalScribe calculate my overall rating? No. It drafts the professional-practice half; SLOs and the overall rating happen in your district's process.
How does the Blueprint career ladder affect this? It ties evaluation to a career ladder and adds requirements like conferences and Peer Assistance and Review. EvalScribe's role is the observation write-up at the center of that work.
If you're evaluating teachers in Maryland, see how EvalScribe drafts in the four Danielson domains and your district's rating scale at evalscribe.com/maryland. Questions, or a school or district license? Reach the team at [email protected].
References
Code of Maryland Regulations, COMAR 13A.07.09 — General Provisions for the Evaluation of Teachers and Principals (the five components; overall ratings of Highly Effective, Effective, Ineffective)
Maryland State Department of Education, Maryland Public Schools (state evaluation model; professional practice and student growth weighted equally; SLOs)
Maryland Education Article, Title 6, Subtitle 10 — Career Ladder for Educators (evaluation systems used with the Blueprint career ladder)
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 COMAR 13A.07.09 and Maryland State Department of Education evaluation guidance.
Last updated on August 2, 2026.
