Our position, and its limits.

Design commitments we take from practice

• Consistent location supports automaticity. Rearranging a learned grid imposes a cost on the person using it, so we treat position as part of the vocabulary.
• Robust systems support all communicative functions — requesting, refusing, asking, commenting, joking, storytelling, social talk and self-advocacy — not compliance.
• Partner modelling matters, and it should never become partner authorship.

What we are evaluating

• Breadth of distinct permanent vocabulary reached over time.
• Proportion of selections made without partner prompting.
• Mix of communicative functions expressed, including refusal and self-advocacy.
• Word searches that end without a selection, as a signal of system gaps.
• Whether promotion from the Context Halo to permanent slots reduces those gaps.

What we will not claim

• That EyeSay diagnoses, treats or cures autism or any other condition.
• That it is clinically superior to any other AAC system.
• That it can determine what a communicator feels, means or intends.
• Outcomes we have not measured in real use.

Working with us

We are looking for families, schools and speech and language therapists willing to evaluate the system in ordinary daily use and report where it fails. Measurement uses derived metrics only; we do not ask for transcripts of what a child said.