Calculators, visualizers and labs for answering AI engineering questions with explicit assumptions. Each tool documents its method, cites its sources and makes the scenario reproducible.
A tool appears here when the English and Spanish versions share the same logic, sources and tests.
Turn tokens, caching, traffic, TTFT, generation speed and concurrency into cost per request, monthly spend, response time and approximate capacity.
Open calculator →Compare your workload cost with Intelligence Index, output speed, TTFT and context while keeping pricing and performance provenance separate.
Open explorer →Separate weights, KV cache and runtime reserve to estimate total memory, memory per GPU, maximum context and approximate concurrency.
Open calculator →Visualize how KV-cache memory and context capacity change with GQA/MQA, precision, concurrency and a configurable memory budget.
Open explorer →Manipulate scores, causal masking, softmax and values to see how one attention head turns a query into a weighted mixture.
Open visualizer →Allocate the window across instructions, tools, history, RAG, the current message, output and safety headroom to surface overflow and future pressure.
Open planner →Measure Precision@k, Recall@k, MRR and nDCG on a visible ranking; test reranking while keeping retrieval quality separate from chunking and overlap footprint.
Open lab →The section grows one tool at a time. There are no empty placeholder pages: an entry appears when it has real interaction, ES/EN parity, provenance and tests.