Three Kinds of Software Survive: Tasklet's Andrew Lee on Competing to be a Horizontal Platform

Tasklet CEO Andrew Lee details the rapid evolution of his company’s AI agent architecture, which has shifted from simple workflow automation to a general-purpose platform utilizing a file-system-based context management strategy. By moving away from infinitely long chat histories toward a bucketed, decreasing-fidelity summarization model, Tasklet optimizes token usage and maintains performance across long-running agent tasks. Lee emphasizes the "mecha suit" paradigm, where the agent’s harness—comprising storage, compute, and tool integration—is as critical as the underlying frontier model. While the company maintains a neutral stance by integrating models from Anthropic, OpenAI, and others, it faces intense competition from its own suppliers. The future of software lies in horizontal agent platforms that replace fragmented SaaS applications, relegating traditional software to either headless API-first services or specialized outcome-based solutions.