Assistant SENDCoAssistant SENDCo

Use of AI

Last updated: March 2026

Overview

Assistant SENDCo offers optional AI writing assistance to help teachers draft and refine SEN Support Plans. AI features are powered by OpenAI and are designed with pupil privacy as the top priority. This page explains exactly what the AI does, what data it sees, and what safeguards are in place.

AI is optional

Every feature in Assistant SENDCo works fully without AI. Creating, editing, reviewing, and exporting plans does not require AI to be enabled. A teacher or school can choose never to use AI features with no loss of functionality.

Consent

AI features require explicit consent each session. The first time you interact with an AI feature after opening the app, a dialog explains what data will be sent, how it is anonymised, and who processes it. You must actively agree before any data is sent. This consent is stored only for the current browser session and resets when you close the tab — important for shared school computers.

What the AI does

The AI assists with drafting text. It can:

  • Improve the clarity and professional tone of text you have written
  • Suggest SMART outcomes based on your assessment notes
  • Suggest provisions and strategies aligned to stated outcomes
  • Suggest next-cycle targets based on review commentary

In addition, a deterministic quality engineruns entirely on your device to check your plan against 22 structural rules drawn from the SEND Code of Practice, Ofsted, and EEF guidance. This includes checking whether outcomes are SMART, whether provisions specify frequency and responsible staff, and whether your plan maintains a coherent “golden thread” across Assess, Plan, Do, and Review. The quality engine produces a score, inline nudges, and guided fix actions — all without AI and without sending any data.

The AI does not make decisions. Every suggestion must be reviewed and accepted or rejected by the teacher before it is saved.

What data is sent to the AI

Only anonymised text fragments are sent. A full plan is never transmitted. The specific text depends on the feature being used, but is limited to:

  • The specific text field being edited (anonymised)
  • Assessment descriptions (anonymised) for context
  • Outcome statements (anonymised) when suggesting provisions
  • Generic provision bank entries (school-level resources, no pupil data)

The plan quality engine (scoring, inline nudges, and fix actions) runs entirely on your device and sends no data anywhere.

What is never sent to the AI

The following are explicitly excluded from all AI requests:

  • Pupil name (replaced with [PUPIL])
  • Date of birth
  • Year group
  • Areas of need categories
  • Medical diagnoses (replaced with [CONDITION])
  • Postcodes, email addresses, phone numbers
  • Staff names (replaced with [STAFF])

How anonymisation works

Before any text reaches the AI, it passes through a five-layer anonymisation pipeline:

  1. Name replacement — the pupil's name and all name parts are replaced with [PUPIL]
  2. PII scrubbing — postcodes, emails, phone numbers, dates, diagnoses, and staff names are detected and replaced with placeholder tokens
  3. Common name detection — approximately 250 common UK first names are checked and replaced, catching references to siblings or other children
  4. Full name pattern detection — any two consecutive capitalised words are treated as a potential name and replaced (with a whitelist for SEND terminology)
  5. Context stripping — the pupil name field is explicitly removed from the data sent to the API

Output safety filtering

AI responses are checked before being shown to you. The filter blocks content containing profanity, violence, discriminatory language, medical advice, or anything inappropriate for an educational context. If a response is filtered, you see a generic message and the incident is logged for review.

AI provider

AI features use OpenAI(model: gpt-4.1-nano) via their API. Under OpenAI's API terms:

  • Data sent via the API is not used to train AI models
  • API data is retained for up to 30 days for safety monitoring, then permanently deleted
  • A Data Processing Agreement is in place between Progress 55 Ltd and OpenAI

Limitations

AI suggestions are generated by a language model and have inherent limitations:

  • Inaccuracy — suggestions may contain factual errors, unsuitable strategies, or targets that do not match the pupil's needs
  • Bias — language models can reflect biases present in their training data, which may result in stereotyped or culturally insensitive suggestions
  • Not a replacement for professional judgement — AI suggestions are starting points only and must be reviewed, edited, or rejected by the teacher

You are responsible for reviewing all AI-generated content before it is saved to a support plan. Do not accept suggestions without checking they are appropriate for the individual pupil.

Questions

If you have questions about how AI is used in Assistant SENDCo, contact us at george@progress55.co.uk

Back to home