Your LLM reads the whole file. It doesn't have to. (opens in new tab)

Coding agents read specs, design docs, and long READMEs every day. Most of the time, they only need a few sections. Yet they load the entire file into context. The hidden cost of "just read the file" Here's a scenario that plays out constantly. You ask your agent to check the error handling section of a 5,000-line API spec. The agent opens the file, reads all 5,000 lines into its context window, finds the 80 lines it needs, and answers your question. The result is correct. But the agent also ...