All lessons
prompt-caching
2 free lessons tagged prompt-caching across AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
AI
advancedContext Engineering for Long-Running Agents
How to manage, compress, and strategically fill the context window in long-horizon agents — covering summarization checkpoints, scratchpad memory, retrieval injection, prompt caching, and compaction triggers.
12 steps·~18 min
AI
intermediateLLM Pricing and Latency: What Actually Drives Cost
How frontier LLM costs and latency actually work in 2026 — input vs output token asymmetry, prompt caching, batch API discounts, TTFT and tokens-per-second, reasoning-model amplification, and when self-hosting breaks even.
10 steps·~15 min