About us
Most AI content is about what's possible. This group is about what's working.
AI in Production is a community for engineers, founders, and technical practitioners who are building with LLMs in the real world — not in demos, not in theory. We talk about the unglamorous stuff: evals, cost control, latency, prompt reliability, RAG that actually retrieves the right things, agents that don't go off the rails, and models that behave the same way in prod as they did in testing.
If you've ever shipped an LLM-powered feature and immediately started watching your API bill, you're in the right place.
What we cover
- LLM architecture and model selection
- RAG, embeddings, and retrieval that works at scale
- Observability, evals, and keeping hallucinations out of prod
- Cost management and inference optimization
- Agents, tools, and multi-model systems
- Real case studies from people who've shipped
No hype. No keynote energy. Just practitioners sharing what's actually working.
Past events
9
