AI & ML
Flow generation through natural language: An agentic modeling approach
Shopify Engineering0 views
We fine-tuned Qwen3-32B into a tool-calling agent that generates Flow automations from natural language—faster, cheaper, and more accurate than the frontier model it replaced, with a weekly retraining flywheel built on real merchant data.
Source:https://shopify.engineering/fine-tuning-agent-shopify-flowPreviousWe replaced Redis with MySQL for inventory reservations—and it scaledNextAutoresearch isn’t just for training models
Related posts
Guests, pets, and what a room-level presence display cannot tell you
0dev.to
How a GPT‑Driven Loop Made AI Videos Physically Accurate – 30% Better!
0dev.to

Your 4K Upscale Looks Worse Because You Picked the Wrong Preset, Not Because 4K Is Bad
0dev.to
Perplexity Decider v1.3: Training, eval, and use cases
0Hacker News

Adapting to AI penetration testing orchestrators: The Modern Security Model
0Cloudflare Blog
AI agent startup LangChain hits $3B valuation
0TechCrunch