Thank you, Singapore. See the photos from our Agentic Patterns workshop at GovTech STACK 2026.

Supertype Notes

Model Serving

Taking trained models off the laptop and into resilient serving infrastructure.

2 articles in this topic

Serving PyTorch Models Using TorchServe

Package a PyTorch model with torch-model-archiver, write a custom handler, serve it through TorchServe's inference and management APIs, then run it in Docker.

SA
Stane Aurelius
12 min read
The Enterprise AI Agentic Stack
From the Supertype shelf

Going deep on Model Serving? We wrote the book.

The same thinking runs all the way through this 12-chapter guide, written by Samuel Chan and ready to read in an afternoon.

Building agents that build your business
Learn it live with our engineers

Building agents that build your business

A two-evening workshop on designing and shipping AI agents that do real work for your business: from the agentic patterns that keep them reliable, to a working multi-agent system that researches, drafts and reports on your behalf.

December 9, 2026Zoom Conferencing (Online)

Save your seatSeats from Rp490.000 (about $27)

Related topics

Keep reading

This is one slice of the catalogue. Browse every topic on the notes index, or subscribe and we will send the next piece your way.

All Supertype Notes
The latest in AI and Enterprise Analytics

We do not resell your data. We respect your privacy and trust.