How can AI help New Hampshire evaluators write teacher evaluations?
How can AI help New Hampshire evaluators write teacher evaluations?
New Hampshire keeps teacher evaluation close to home. There is no single statewide rubric that every district must use. Instead, each school board adopts its own teacher performance evaluation system, developed with teachers and principals, and most districts build that system around the Danielson Framework. That's where AI fits. It can help draft the professional-practice write-up — mapping observation evidence to the right Danielson component and putting it in the framework's own language. What it can't do is measure student performance, combine the pieces into a final rating, or replace an evaluator's judgment. This post walks through where AI helps, where it doesn't, and what to look for.
What New Hampshire's system actually is
New Hampshire's evaluation requirement lives in the state's Minimum Standards for Public School Approval, Ed 306, and in statute at RSA 189:1-a. The rule directs each local school board to adopt a teacher performance evaluation system, with the involvement of teachers and principals, for use in the district. The design decisions happen locally.
The state does offer guidance. The New Hampshire Task Force on Effective Teaching outlined a recommended framework for a district-designed system built on multiple measures — professional practice plus student performance. But that framework is advisory. What the state requires is that a district have a system, developed collaboratively; it does not hand districts a single rubric or a single rating scale.
Danielson is the common choice
Because districts choose their own professional-practice instrument, there's real variation across the state. But most New Hampshire districts have landed on the same one: the Charlotte Danielson Framework for Teaching. It organizes the observed and documented work of teaching into four domains:
Planning and Preparation. Knowledge of content, students, and resources, and coherent instructional design and assessment planning.
Classroom Environment. A culture of respect and rapport, clear expectations, managed routines, and a 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 Responsibilities. Reflection on practice, accurate record-keeping, communication with families, professional growth, and contribution to the school community.
New Hampshire doesn't mandate a set of rating labels. A district using Danielson typically works from its four levels — Unsatisfactory, Basic, Proficient, Distinguished — while a district using its own instrument may use different terms.
Multiple measures and three teacher tracks
Two features shape how the work happens. First, New Hampshire systems use multiple measures: professional practice is combined with a student-performance measure, but the balance is set locally rather than by a statewide formula. Second, many district systems organize teachers into three tracks — beginner teachers, continuing-contract (tenured) teachers, and teachers on an improvement plan following a substandard evaluation — each with its own observation and evaluation rhythm.
That structure means the professional-practice documentation shows up in different cadences for different teachers, but the underlying task — evidence against the Danielson domains — is the same.
After the observation: where the work piles up
The observation itself is familiar work for an experienced New Hampshire evaluator. The write-up that follows is where the hours go: taking fragmentary observation notes and organizing them as evidence against the right domains, settling on a defensible level for each, and drafting feedback a teacher can act on — across a caseload that may span all three tracks.
Where AI helps with the New Hampshire write-up
The strongest fit between current AI and New Hampshire'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. 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 New Hampshire specifically, the value is drafting in the Danielson framework's own language and toward your district's levels, so the write-up is ready for the record 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 New Hampshire built the system.
AI cannot measure student performance. Tools like EvalScribe draft the professional-practice component. The student-performance measure, and the way it combines with practice into a summative rating, are handled in your district's system.
AI cannot run the local process. Teacher tracks, improvement plans, and the teacher-and-principal involvement Ed 306 requires are collaborative, human parts of New Hampshire's approach by design.
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 how New Hampshire 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. Those errors are the kind that surface at the worst possible moment.
What to look for in an AI tool for New Hampshire
A few questions worth asking before committing a tool to this work.
Does the tool actually know the Danielson domains, or does it produce generic "good teaching" language?
Does it draft toward your district's adopted system and labels rather than assuming a single statewide scale?
Does it stay in its lane, drafting professional practice and leaving student performance and the summative to your district?
Does it work across your teacher tracks — beginner, continuing-contract, and improvement-plan?
Where does your observation data live? Is it stored on the vendor's servers, or used to train models?
How EvalScribe handles New Hampshire evaluations
EvalScribe is built around the four Danielson domains that most New Hampshire districts use. 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 rubric levels. 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 New Hampshire's structure calls for them. First, EvalScribe drafts the professional-practice write-up, for any of your teacher tracks. The student-performance measure, the combination into a summative rating, and the local process are run by your district, not the app. Second, because New Hampshire districts design their own systems and most build them around Danielson, EvalScribe fits districts using the Danielson Framework or a Danielson-aligned local rubric most directly. 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, that adds up to dozens of hours back — hours that can go to the coaching and feedback the evaluation is meant to support. More detail on the New Hampshire workflow is available at evalscribe.com/newhampshire.
Frequently asked questions about New Hampshire evaluations and AI
What evaluation model does New Hampshire use? It's local-control. Each district adopts its own system under Ed 306 and RSA 189:1-a, and most build it around the Danielson Framework. EvalScribe is built around Danielson.
Does New Hampshire require a specific rubric? No single statewide one. The state requires each district to adopt a system with teacher and principal involvement; districts choose or build the rubric, and most use Danielson.
How is student performance handled? New Hampshire uses multiple measures, with the balance set locally. EvalScribe drafts professional practice; student performance and the summative stay with your district.
Does EvalScribe work across the teacher tracks? Yes — it drafts the professional-practice write-up for beginner, continuing-contract, and improvement-plan teachers alike.
Can I use it with our own rubric? Often, yes — most New Hampshire instruments are Danielson-aligned. Confirm your district's system, or email [email protected].
If you're evaluating teachers in New Hampshire, see how EvalScribe drafts in the Danielson domains at evalscribe.com/newhampshire. Questions, or a school or district license? Reach the team at [email protected].
References
New Hampshire Department of Education, Minimum Standards (Ed 306) (the rule requiring each district to adopt a teacher performance evaluation system)
New Hampshire Code of Administrative Rules, Part Ed 306 (adopt a teacher performance evaluation system, with the involvement of teachers and principals, pursuant to RSA 189:1-a, III)
U.S. Department of Education / REL Northeast, Redesigning teacher evaluation: Lessons from a pilot in New Hampshire (Danielson's four domains in New Hampshire districts; the three teacher tracks)
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 New Hampshire Department of Education's Minimum Standards (Ed 306), RSA 189:1-a, and federal research on New Hampshire's evaluation pilot.
Last updated on August 2, 2026.
