Bring Structure to Your Agent Workflows

This blog was modified slightly on Aug 26, 2026.

This week, we added three new commands that make it easier to review agent-generated code: entire recap, entire review, and entire labs.

Recap Recent Agent Activity

Let's begin with entire recap, a new command that shows how you and your team are using AI across your repositories, broken down by agent. Choose a time window with --day (the default), --week, --month, or a rolling --90 days. Use --view you|team|both to switch between your activity, team activity, or a side-by-side comparison, and --agent to filter to a specific agent.

As soon as you're signed in, entire recap opens an interactive terminal by default, giving each agent a panel with sessions, checkpoints, token usage, files touched, top skills and MCP servers, and tool mix. Or, if you prefer plain output suitable for scripts or CI, you can use --static to run the command.

Review Your Branch with Multiple Agents

The new entire review command uses your configured AI reviewers to check the code changes on your current branch.

On the first run, an interactive picker writes .entire/settings.json with the skills and per-agent prompts to use. Then, when a review starts, Entire shows the scope and adds the checkpoint history for each commit in scope to the agent prompt. That gives the reviewer the context behind the changes before it evaluates them.

You can configure more than one agent, including Claude Code and Codex, to run reviews in parallel, and you can always use --edit to reopen the picker or --agent NAME to override the default agent. entire review runs agent reviews concurrently against the same scope and shows the results side by side in a live terminal. Afterward, the command records the review in the next checkpoint so its metadata stays with the commit, giving you a record of reviews for posterity.

Run Labs to Try Experimental Workflows

Finally, we've introduced a command called entire labs that lists experimental Entire workflows for you to explore.

Run it to see which experimental commands are currently available, and deploy them in your branch to see how they work in practice. You may even find a sneak peek inside: future experimental workflows will appear under this command even while they're still in development.

Get Started

Update the CLI to version 0.6.1 or later, then run these commands from any enabled repository:

$entire review --help
entire recap
entire labs