# Governing agent autonomy with Auto-review

Source: [Cursor](https://cursor.com/blog/agent-autonomy-auto-review)  
Feed7 permalink: https://feed7.dev/p/agent-autonomy-auto-review-10ce67w  
Published: Unknown  
Trust: Official Source (official_source)

## Why Included

Cursor's Auto-review puts a classifier agent between your agent and risky actions: it blocks about 4% of actions, versus ~40% under old enterprise defaults, letting agents run longer without going fully unsupervised.

## Source Summary

**The gist** Cursor shipped **Auto-review** (June 11, 2026): a classifier agent that inspects each agent action in context — using ReadFile, Grep, and similar tools — before it executes. It blocks about **4%** of actions versus a **~40%** enterprise-baseline block rate, and only **~7%** of chats see a user interruption. It runs in the same RPC stream as the parent agent to keep latency low.

## Practical Implication

**Why it matters** This treats autonomy as a **dial, not a switch**: instead of approving every command or allowing everything, a second model judges whether the next action crosses a real boundary. On by **default for new users**; existing users enable it in **Settings > Agents**. Worth trying if permission prompts are your bottleneck.

## Agent-Ready Context

**The gist** Cursor shipped **Auto-review** (June 11, 2026): a classifier agent that inspects each agent action in context — using ReadFile, Grep, and similar tools — before it executes. It blocks about **4%** of actions versus a **~40%** enterprise-baseline block rate, and only **~7%** of chats see a user interruption. It runs in the same RPC stream as the parent agent to keep latency low.

**Why it matters** This treats autonomy as a **dial, not a switch**: instead of approving every command or allowing everything, a second model judges whether the next action crosses a real boundary. On by **default for new users**; existing users enable it in **Settings > Agents**. Worth trying if permission prompts are your bottleneck.

**Watch out** It's **early** and covers only **local agents in the desktop app**. A 4% block rate means trusting the classifier on the other 96% — it was evaluated on **6,122 labeled rows** from Cursor's internal sessions and synthetic cases, not your codebase.

## Context Map

- Layer: tools
- Domains: coding
- Topics: agent-reliability, harness-engineering, coding-agents

## Uncertainty

- It's **early** and covers only **local agents in the desktop app**. A 4% block rate means trusting the classifier on the other 96% — it was evaluated on **6,122 labeled rows** from Cursor's internal sessions and synthetic cases, not your codebase.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.