Every report your team writes, built the same way.
AUTOMATA for districts gives your whole assessment team one report engine, with your district's templates, eligibility criteria and forms built in and connected to the systems you already use. Your psychologists upload the score reports and records, review the draft, and sign.
District plan · District and group subscription prices are negotiable · See all plans · Ask your district to fund it · For directors · For counsel
Development preview: This page describes the intended workflow. Desktop release availability, supported features and deployment arrangements must be confirmed for your setup. View release status.
One system for every evaluator.
For a team of 15 writing 80 reports each: 5,400 hours back. That's like adding 3.5 full-time psychologists to your team for a school year.
1,200 reports × 4.5 hrs = 5,400 hrs ÷ 8 hrs a day ÷ 190 school days ≈ 3.5
Your district's standard
District report templates, eligibility criteria and forms built in, so every report follows the same structure and wording.
Shared caseload
One data sheet feeds every report, with a shared template library and house-style rules across the team.
Verified numbers
Every score in the prose traced to its table and every descriptor checked against the publisher's band. Mismatches are flagged, never silently fixed.
An audit trail
A log of every automated check and every human approval, so you can show how each report was built.
Onboarding and training
Training for your assessment team from a practicing school psychologist who writes these reports every week.
Built around the way your district already works.
Every district's paperwork is different. We set AUTOMATA up around yours instead of asking your team to change how they work.
- Your student information system and Google Workspace, connected so student details come in without retyping
- Your report templates, section order and required headings
- Your eligibility criteria and forms, including the wording your team is required to use
- Your caseload sheet or tracking system as the one place scores live
- The instruments your team uses: send a redacted score report for any test AUTOMATA does not read yet and we add it
Every automated change is a proposal your psychologist accepts or rejects. Nothing goes into a report without a yes.
Built for FERPA from the first draft.
- Drafting runs on de-identified records; names and identifiers stay in your files
- Nothing identifying is stored by us
- Data-processing agreement, FERPA and HIPAA documentation, and a security review on request
The “Settled Findings” AI model: zero hallucinated scores, zero downtime.
Districts rightfully ask: how does the AI work, and can it make up numbers? In AUTOMATA, the language model is never allowed to interpret raw scores or calculate cutoffs on its own. All clinical calculations and classifications are locked deterministically on your machine before any phrasing occurs.
Where it is controlled
District and evaluator controlled: Evaluated in main.js (composeNarrativesStep) and governed under Settings > AI.
When “Compose Test Narratives” runs (or during full automated runs), the app verifies your district AI policy. If enabled, it calls ai-writer.js (composeWithAi) using encrypted local keys (Anthropic Claude, OpenAI, or Groq). If disabled, it runs 100% offline.
The “Settled Findings” rule
Local classification first (narratives.js): The local deterministic engine computes every exact score, percentile, publisher descriptor band, relative strength/weakness, and classroom impact statement first.
Phrasing only (ai-writer.js): Only that structured packet of verified findings is sent to the LLM to format natural clinical prose.
Strict FERPA privacy: The student’s real name never leaves your Mac or district machine—it is anonymized as STUDENT before transmission and restored locally after the prose returns.
Verification & automatic local fallback
Deterministic number verification: Every single number, score, and percentile returned by the AI is cross-checked against the original raw test data. If any score or percentile is missing or altered, the AI output is thrown away.
Zero-downtime local fallback: If the district network drops, an API key limits, or AI is turned off, AUTOMATA seamlessly switches to narratives.js’s built-in local clinical text generator. You always get complete, publication-ready narratives with zero downtime.
From one report to the whole team.
Walkthrough
A live walkthrough of AUTOMATA on one of your own reports.
Scope
We map your templates, eligibility criteria, forms and the systems AUTOMATA needs to connect to.
Build
We build your district's templates and connections and test them on real reports with your team.
Train and launch
Onboarding for your assessment team, then every evaluator writes on the same system.
Bring us one of your reports.
We will walk your team through AUTOMATA on one of your own reports and scope what your district needs.
Talk to us