Learned indexes are capable of predicting the accurate location of data in storage by learning the data distribution. These indexes can significantly reduce storage consumption while providing efficient query processing. Existing learned indexes are mostly optimized for read-only queries, but inadequate in supporting insertions and updates. In an attempt to address the challenges faced by learned index, this study proposes a workload-adaptive learned index named ALERT. Generally, ALERT employs a Radix Tree to manage variable-length segments, where each segment contains a linear interpolation model with a maximum error-bound. Meanwhile, ALERT utilizes an insertion memory buffer to reduce the cost of updates. Following the database-cracking approach, the study proposes adaptive index maintenance during the run-time processing of point queries and range queries. The maintenance technique is implemented by performing workload-aware dynamic re-organization on the insertion buffer. Experimental results confirm that, when compared to state-of-the-art learned index, ALERT achieves competitive results as it reduces the index's average construction time by 81%, the average memory utilization by 75%, the average latency of insert by 50%, while maintaining competitive read performances. The average query latency of ALERT is also reduced by 15%, owing to its effective workload-aware optimization.