AI Media-Buying Agents: L1, L2, L3 Autonomy Explained (2026)
dev.to
TL;DR: Autonomous media-buying agents that spend without human review are a lawsuit waiting to happen. Bounded autonomy in three tiers is the working pattern - L1 the agent recommends, L2 a human confirms, L3 the agent acts inside a strict KPI envelope with kill switches. Skip L3 for regulated verticals until you have three months of L1/L2 data proving the agent does not do stupid things. The conversation about AI agents has bifurcated in 2026. On one side, autonomous agents that plan, act, a