Seekho Platform v2
Technical & AI Product Management
An offline-first curriculum engine for local educators that eliminates API timeout failures with async event-driven delivery.
By Shehryar Hassan·2025-11-01
Next.jsTypeScriptSupabaseInngestTailwind CSSLLMs
seekhopunjab.vercel.app
The Product VisionScaling a localized educational generator from a fragile prototype into a production-grade enterprise application.
The User Problem
Processing large generative lesson plans caused massive latency. Standard API gateways kept dropping the connection during long compilation loops, and users abandoned the platform whenever the interface froze mid-generation.
Architecture
- Moved from synchronous requests to an asynchronous, event-driven pipeline using Inngest background workers.
- Split long generation loops into siloed queues for syllabus mapping, AI content generation, automated remediation, and WhatsApp parent notifications.
- Persisted intermediate state in Supabase so users can close the browser mid-run and return to a completed plan later.
Product & Growth Impact
- Reduced processing failures to 0% by shifting heavy computation off the request thread.
- Kept the UI fully interactive during long AI workloads, lifting retention through generation.
- Wired automated WhatsApp hooks for scalable parent engagement and organic feedback loops.