Never Stranded Again: How I Built an Edge AI Bus Guardian for My Friend Tejas Using TabPFN & SerpApi

Description and use

KTCL CommuteShield predicts stranded risk and sends a Telegram alert with the required top‑up before the nightly sync cutoff.

Problem

Tejas’s KTCL smart card balance often fails to sync before the nightly batch, causing him to be stranded at the depot when he needs to travel for classes, labs, or evening football matches.

Outcome

Tejas received an emergency alert on Friday night that saved him from being stranded at the depot the next morning.

Workflow

• Run agent at 8:00 PM IST
• Scrape live card balance from KTCL portal
• Ingest tomorrow’s calendar events
• Query SerpApi for live road conditions
• Feed 7‑dimensional feature vector to TabPFN
• If stranded risk ≥60% send Telegram alert with top‑up recommendation

Evidence

If a commuter recharges their card online at 12:05 AM, the money leaves their bank account, but the balance fails to sync to the depot turnstile until the following evening's batch.

Source

KTCL CommuteShield runs locally on Tejas's laptop every evening at 8:00 PM IST (nearly 4 hours ahead of the depot sync deadline).

Source

If genuine risk exists (Stranded Risk ≥ 60%), it sends an actionable alert to Tejas's phone before midnight with the exact minimum recharge amount needed.

Source

"The 11:59 PM depot cutoff stranded me twice last semester during monsoon examinations. CommuteShield pinged my Telegram at 8:15 PM on Friday warning me about the Wadi turf detour and gave me the exact recharge figure. That alert saved me from standing stranded at Margao depot at 7:30 AM."

Source