At AIEdx the focus is production-grade agentic systems — not slide-deck demos. FetchLens surfaces agent visits that classic analytics undercount.

FBA Lab is where that work becomes hands-on study. Walk real inference and training code through curated blocks, teacher prompts, and interactive diagrams — no GPU required. The Speedrun track follows nanoGPT optimization from baseline to sub-3-minute runs; Qwen C traces GGUF loading, buffers, forward pass, tokenizer, and generation in plain C. Study mode lets you explore architecture and code paths at your own pace.