How much can you delegate to agents?
TLDR Dev
PostHog's Jina Yoon outlines a framework for deciding how much autonomy to give AI agents based on task checkability and reversibility rather than model capability alone. The framework defines four levels: assistant mode for hard-to-check, hard-to-undo work; human-in-the-loop for hard-to-check, easy-to-undo work; agent delegation for easy-to-check, hard-to-undo work; and self-driving mode for easy-to-check, easy-to-undo work. The approach enables faster shipping by automating low-risk tasks through deterministic checks, reversibility guarantees, and structured guardrails rather than relying on human review as a bottleneck.
Why it matters
An 8-minute read exploring how much autonomy and delegation is appropriate when working with AI agents.
