Five-stage spoken learning loop with supplementary visual affordances¶

Design · All designs
Evidence · no claims cited

Description¶

Kutti AI's interaction design is "a spoken conversation with five stages": welcome (a single large haptic-enabled control), spoken lesson delivery paced with natural pauses, voice response captured by a large microphone control or hands-free mode, adaptive response (encouragement, hint, or simplified question), and a spoken summary with an engagement score (0–100). Visual affordances—screen-reader compatibility, large touch targets, haptic confirmation, high-contrast scheme—are strictly supplementary for low-vision users and sighted caregivers.

Design Implications¶

Context¶

Requirements¶

Visual elements may exist for sighted caregivers but must never be required (R1)

Constraints¶

Target Learners¶

visually-impaired children
low-vision users and sighted caregivers

Learning Goals¶

completing an entire learning session through speech alone

Claims¶

Examples¶

-

Key Sources¶

Kadharmoideen Fadurudeen. (2026). Kutti AI: A Voice-First, Offline-Capable Learning Companion with Real-Time Struggle Detection for Visually-Impaired Children. https://arxiv.org/abs/2607.22377

Page metadata

Field	Value
`type`	`design`
`id`	`five-stage-spoken-learning-loop`
`title`	`Five-stage spoken learning loop with supplementary visual affordances`
`description`	`Kutti AI's interaction design is "a spoken conversation with five stages": welcome (a single large haptic-enabled control), spoken lesson delivery paced with natural pauses, voice response captured by a large micropho...`
`status`	`review`
`generated`	by `process:settle-candidates` on `2026-10-11`
`trust`	unverified — no one has confirmed this page's content
`sources`	1 — `kadharmoideen-fadurudeen-2026`

Frontmatter is the page's machine-readable record — see the Schema & Guide.