Kelas Sekejap: Can KJ and Shahril’s AI app actually make you speak better English?
- ID
- 33508
- Status
- summarized
- Published
- 09 Oct 2026, 11:49 AM
- Fetched
- 09 Oct 2026, 11:50 AM
- Provider
- SoyaCincau
- Category
- malaysia-tech
- Original URL
- https://soyacincau.com/2026/10/09/kelas-sekejap-can-actually-make-you-speak-better-english/
- Source URL
- https://soyacincau.com/feed/
Summary
- Score
- 6.0
- Created
- 09 Oct 2026, 11:50 AM
- Tags
- Audience
- developersvibe_codersai_ml_learners
What happened
Kelas Sekejap is an AI-powered English speaking-practice app built for Malaysians and launched earlier this year, reviewed hands-on by SoyaCincau's Janarrthine Kannan. The review found the voice recognition accurate enough to capture stutters, hesitations and pauses, alongside a Bahasa Malaysia/English UI toggle, a daily vocabulary word that drops you into a lesson, profile controls for practice rhythm and topics, and goal prompts that keep conversations structured. The weak spot is dialogue handling: the app struggles with longer, multi-layered or controversial answers and starts 'talking in circles' — asked what to do at the beach, it refused to choose and listed options for the user to pick instead.
Why it matters
For anyone building a voice-first or conversational LLM product, the split is the useful part: the speech-recognition side handled messy human input well, while multi-turn dialogue was the failure point — long answers, layered questions and contentious prompts caused circular replies and a refusal to commit to a decision. Concretely, that argues for scoping expected answer length, deciding how your app handles provocative input, and forcing the model to pick one recommendation instead of deferring with a menu. Note the excerpt is truncated, so the review's comparison verdict against Duolingo and its final recommendation are not in the text.
Discussion angle
Run the same two prompts against your own agent — a vague planning question ('what should we do at the beach?') and a deliberately controversial take — and see whether it commits to an answer or hands back a list. That single test exposes the same multi-turn weakness this review hit.