---
title: "Review agent work · intentic"
description: "Every agent starts in plan mode, permission is a per-turn dial, and finished work is reviewed diff by diff before anything lands in your tree."
url: "https://intentic.dev/features/review/"
---

Review

# It proposes. You approve. Nothing is merged until you read the diff.

Every agent plans first, then waits. Review each file before you accept the change.

[Create your workspace](https://app.intentic.dev)[Open the live workspace](https://intentic.dev/demo/)

![The docked chat: the agent's thinking block, a Read tool call, a four-step plan for adding Stripe checkout, and two buttons: approve, or keep planning.](https://intentic.dev/_astro/chat-plan.C6sE25hd_ZxIjfG.webp)

- Plan first

 every agent reads, proposes, then waits for you
- Permission dial

 how much it may do unattended, per turn
- Accept or discard

 one button each; no change is accepted by surprise

## The plan is the contract

Before editing, it shows which files it will touch. Approve, and the plan becomes a to-do list you watch.

- Thinking, tool calls and to-dos stream as they happen, never summarised after the fact
- Steer mid-turn: a message lands in the running turn instead of queuing behind it
- Continue the same conversation on your phone and unblock an agent with one tap

## Permission is a dial, not a switch

A pill sets how far the agent may go each turn: strict for a migration, loose for a changelog.

## Reviewed by file, not by wall of text

Work is grouped by file, so a 400-line change reads as six decisions. Unread files stay marked until you look.

acme-shop · /workspace

![The workspace Changes tab: five uncommitted files grouped by repo with their line counts, and the diff of one of them open beside the list.](https://intentic.dev/_astro/workspace-changes.aomkC5F2_zNpR8.webp)

## The review boundary is a real branch

Accepting the agent's work adds ordinary git changes you can stage, amend or revert.

One base commit, one branch each

agent/checkout-stripe

its own worktree, its own checkout

agent/soft-deletes

its own worktree, its own checkout

agent/latency-p99

its own worktree, its own checkout

accept one at a time, after you have read the diff

Your checkout

Untouched until you accept the work, and still yours to change or revert afterwards

## Steer it by what it knows, not by nagging

You can't make the model smarter, but you can equip it: better context and tools each turn.

### A prompt a system prompt and a few .md files

- Can describe tools, but cannot install them.
- Cannot access your code, data or services.
- Starts from the same blank context every run.
- Produces output you must apply yourself.

### The whole environment a sandbox you can open and change

- Development tools and libraries are installed.
- Connects to your repositories, databases and services.
- Loads the context you chose on every run.
- Does the work and shows every file change as a diff.

## One workspace, two operators

You and the agent share one workspace. You open the same editor, files and terminal it uses.

Surface

You

The agent

Search

the workspace search box

`iq` from Bash

Terminal

a docked terminal tab

shell commands

Files

the tree and the editor

Read and Edit

Network

the VPN panel

/usr/local/bin/vpn

You and the agent use the same search, terminal, files and network connection, so both always see the current state.

[Guide Is an AI agent's summary of its own diff enough to merge on? A straight answer, the approaches that are not this product included.](https://intentic.dev/guides/review-ai-generated-code-changes/)

[Next Host → Run on hardware you own](https://intentic.dev/features/host/)

[Create your workspace](https://app.intentic.dev)[Read the quickstart](https://intentic.dev/docs/quickstart/)
