This document is provided for informational purposes during our pre-launch period. A comprehensive, attorney-reviewed version will be published prior to the platform processing student data.

AI TRANSPARENCY

How Our AI Handles Your Data

A plain-language explanation of what our Clinical Intelligence Engine does, what it doesn't do, and how student data is protected throughout.

Last updated: September 29, 2026

What Our AI Does

SPEDScribe's Clinical Intelligence Engine generates draft clinical documentation from redacted session transcripts. A SOAP note restates what the provider dictated, in clinical language, and is designed to add no interpretation, diagnosis or comparison the provider did not dictate. The engine draws on reference material that includes:

✓Score interpretation bands for 80+ assessment tools across 7 clinical disciplines

✓The Endrew F. standard for IEP goal ambition and appropriateness

✓California Education Code timelines for evaluation, eligibility, and IEP development

✓Evidence-based practice guidelines for speech-language pathology, occupational therapy, school psychology, and special education

✓L1 transfer pattern reference data for 16 California languages

What Our AI Does NOT Do

-Make clinical decisions. Licensed providers must review, edit, and approve every draft before filing it.

-Diagnose students. A SOAP note is designed to state no diagnosis or disorder the provider did not dictate.

-Determine eligibility. Eligibility decisions are made by the IEP team, not the AI.

-Replace professional judgment. The AI is a drafting assistant, not a clinician.

-Learn from or retain student data between sessions. Anthropic, our AI provider, does not train on customer inputs under their commercial terms; SPEDScribe does not hold a Zero Data Retention enterprise agreement; standard commercial retention behavior applies.

Data Handling

Personal identifiers are processed through layered server-side redaction before AI processing. The AI processes redacted text designed to be free of student names, dates of birth, and other identifiers; redaction reduces exposure, not a guarantee of complete removal.

Our AI provider (Anthropic) does not use customer inputs or outputs to train models under their commercial terms. Inputs and outputs are retained briefly for abuse detection and to meet legal obligations before deletion. SPEDScribe does not hold a Zero Data Retention enterprise agreement with Anthropic; standard commercial retention behavior applies.

No student data has been used to train any AI model in our pipeline. Our processing architecture is designed to prevent model training on student data through the combination of contractual no-training terms with our AI provider and layered server-side PII redaction.

Human Oversight

A SOAP note is designed to contain only what the provider dictated or entered for the session. It is designed to carry a [CLINICIAN REVIEW NEEDED] tag, in fixed words, in three places:

✓A section with nothing dictated for it holds the tag instead of filled-in content

✓A session with no IEP goal given, in the goals field or in the dictation, ends its Assessment with the tag

✓An error pattern the provider documented that the language reference data does not cover gets the tag after the provider's own assessment

Other documents, such as PLAAFP statements and progress reports, can carry review flags as well. Providers must review, edit, and approve all documentation before filing it.

Accuracy and Limitations

AI-generated documentation is a draft tool. It may contain errors, omit relevant clinical information, or misinterpret transcript content. The provider reviewing the document bears full professional responsibility for its accuracy, clinical appropriateness, and compliance with applicable professional standards.

We test changes against written example dictations that contain no student data. We do not currently collect accuracy metrics or clinician edits from your use.

Bias Mitigation

Our Clinical Intelligence Engine includes built-in protections against disproportionate identification and over-representation:

-A SOAP note is designed never to call an observation a language difference or a disorder unless the provider did: that judgment belongs to the provider and the IEP team

-L1 transfer pattern reference data for 16 California languages (Spanish, Vietnamese, Cantonese, Mandarin, Filipino/Tagalog, Arabic, Korean, Hmong, Punjabi, Russian, Farsi/Persian, Armenian, Ukrainian, Japanese, Pashto, Dari): when a provider documents a speech-sound error the data does not cover, the note is designed to carry a fixed review tag after the provider's own assessment instead of guessing

We welcome feedback on any AI-generated content that appears to reflect bias. Contact us at support@spedscribe.ai.

Questions

For questions about our AI systems, data handling, or to report a concern:
support@spedscribe.ai