Where AI gets
shipped, not pitched.
The Inference Hub is a community of AI practitioners trading real production lessons: talks, events, and two active chats. Free to join, always.
Where we've been
Get in the room
Upcoming events
How do you build agents that stay on task for weeks, not minutes? A webinar on context management, memory, and architectures for long-horizon AI systems.
Utilization looks healthy and throughput still is not there. With Valar, we dig into measuring GPU inference properly: where workloads stall, which numbers matter, and how to read them.
How AdTech actually works, from real-time bidding to attribution, and what AI is really changing in production. No prior AdTech knowledge assumed. Live Q&A at the end.
Follow us on Luma and new events land in your inbox the moment they go live.
Built by practitioners
The Inference Hub is a community of people who ship AI systems for a living. We meet to trade real production lessons: what breaks, what scales, and what it actually costs. No vendor pitches, no hype decks.
AI, explained properly
The Academy is our library of plain-language explainers: how this stuff actually works, from SVMs and XGBoost all the way to LLMs, RAG, and agents. Written by practitioners, free for everyone.
What membership gets you
Regular sessions with engineers shipping AI to production, online and in person.
Daily chatter on WhatsApp, deep technical threads on Slack. Zero spam, no vendor pitches.
What breaks, what scales, and what it actually costs, from people who've paid the bill.
The next event is already on the calendar.
One short form makes you a member. The next event invite lands in your inbox, and the chats are waiting.