The case for small, legible agents

By a contributing engineer · 2026-04-10

The industry has spent two years racing for the largest possible context window and the most opaque possible reasoning chain. There is an argument — unfashionable, but I think increasingly correct — that the next wave of useful work will come from the opposite direction: agents small enough to reason about, narrow enough to trust, and legible enough that their mistakes can be explained rather than merely apologised for.