Artificial intelligence is transforming traditional paper textbooks into adaptive learning systems that can diagnose learners, recommend tasks, and provide formative feedback. This paper investigates the structure and application of an AI‑driven practical English textbook, proposing a five‑layer architecture: knowledge mapping, learner profiling, task generation, feedback orchestration, and teacher‑side governance. A prototype was deployed in an eight‑week teaching experiment with 186 non‑English‑major undergraduates. Compared with a static digital textbook, the system raised unit completion accuracy from 72.4% to 84.9%, increased average speaking task scores by 10.8 points, and cut teacher correction time by 31.6%. The results indicate that an AI‑driven textbook can preserve curriculum stability while delivering personalized learning paths, abundant practice materials, and traceable classroom data.
Review: The study provides solid empirical evidence for the feasibility of AI‑enhanced language instruction and points toward scalable intelligent textbook solutions.