The problem Cognivo solves

Modern knowledge work is fragmented. Ideas, goals, tasks, and plans live across browser tabs, notes apps, and scattered documents — with no spatial structure and no way to see how they connect. Traditional tools are linear and passive; they store information but don't help you think or plan.

Cognivo is an AI-powered infinite visual canvas for productivity and life-mapping. It turns scattered thoughts into structured, interconnected knowledge — and actively helps you work smarter:

1. Smart Brain Dump: Speak or paste your thoughts; AI automatically sorts them into the Eisenhower Matrix (Urgent/Important grid) so you instantly know what to act on.
2. YouTube Roadmap Extractor: Drop any YouTube URL and get a step-by-step learning roadmap extracted directly onto your canvas — no manual note-taking.
3. Conflict Detection: Flags overlapping deadlines and illogical task dependencies before they derail your plans.
4. Time Reality Check: Warns you if your total workload exceeds available time before a deadline — a reality check your to-do list never gave you.
5. Persistent Canvas: Everything auto-saves to localStorage. Your second brain is always where you left it.
6. Voice Input: Speak thoughts directly onto the canvas via Speech-to-Text (Chrome/Edge).

Whether you're a student mapping a semester, a founder planning a product, or anyone trying to turn mental chaos into clarity — Cognivo makes thinking visible and planning honest.

Challenges we ran into

1. Persistent canvas state: Re-hydrating Zustand + localStorage caused node position drift and z-index conflicts in React Flow — fixed with careful state normalization.

2. Gemini structured output: Early API responses mixed JSON with markdown fencing, breaking parsers — resolved with strict prompt formatting and fallback sanitization.

3. YouTube transcript extraction: Transcripts aren't guaranteed for all videos. Handled missing/auto-generated transcripts gracefully with fallback prompting.

4. Time Reality Check logic: Normalizing task durations across incomplete deadline fields and freeform user input was tricky to get accurate.

5. Render cold starts: ~30–50s cold start on free tier made demos feel broken — added a "warming up" loading state to manage expectation.

6. Voice input compatibility: Web Speech API inconsistencies across browsers — scoped to Chromium with a clear fallback message for unsupported environments.