Building fun and creative messaging experiences on WhatsApp
summary
Live demo of a WhatsApp image-to-art pipeline that actually runs: users send a photo to a Twilio webhook, the app downloads Twilio-hosted media, forwards the image and a tailored prompt to the OpenAI image API, then applies a deterministic Sharp overlay and returns a hosted image via WhatsApp. It logs each SID, shows a carousel/dashboard, handles rate limits and three common failure modes (landscape orientation, unrecognizable subjects, copyrighted characters) and says most failed requests succeed on a simple resend.
AI-written summary · about
chapters (18)
- 0:00Introduction
- 1:56Communication matters today
- 5:26Messaging evolution SMS to RCS
- 10:03Businesses prefer messaging
- 13:32Messaging trends behavior
- 16:26Engaging interactive messaging
- 21:25Frictionless drives action
- 22:50Live demo intro
- 24:58AI anime image generator
- 31:56Handling AI errors
- 36:52Sending images back
- 41:01Testing real interactions
- 44:07Dashboard analytics
- 48:43System architecture
- 51:36Debugging Twilio tools
- 53:18Twilio sandbox
- 55:03Twilio vs WhatsApp
- 57:49Call to action resources
related talks
01h 01mBuilding fun and creative messaging experiences on WhatsApp
59mHow to Build a Quokkabot
28mScrew the Browser! Build ChatGPT via SMS
26mHow to enable personalised experiences using Conversational.
01h 20mKeynote
19mThe Reverse Magic Trick
08mThe Architecture of Meta Business Agent on WhatsApp
08mUnified Onboarding on WhatsApp