Everyone is writing about the Agents Window. The parallel agents. The cloud handoff. The rebuilt interface from scratch under the codename Glass.
Those are the headline features and they deserve the coverage. But after spending serious time in Cursor 3 since it shipped on April 2, 2026, the features that have actually changed how I work are not the ones in the announcement post.
Here are the Cursor 3 features that are quietly doing the most useful work — and that most developers have either not found or not fully understood yet.
1. Design Mode — Point at UI Elements Instead of Describing Them
This one is buried in the changelog and barely mentioned in the main announcement.
In the Agents Window, you can activate Design Mode to annotate and target UI elements directly in the browser. Instead of writing a prompt like "the button in the top right corner of the navigation bar that appears on hover" — you point at it. The agent knows exactly what you are referring to.
This sounds small. It is not small.
Anyone who has spent time trying to describe UI context to an AI model knows the problem. You spend more words explaining what you are looking at than it would take to just fix it yourself. Design Mode collapses that entirely. You point. The agent acts.
To access it: open the Agents Window with Cmd+Shift+P -> Agents Window, then activate Design Mode from the agent toolbar. It only works in the Agents Window, not the traditional IDE view — which is probably why most developers using the old IDE interface have not found it yet.
2. The PR Review Experience That Replaces Your Whole Review Workflow
Cursor 3 shipped a PR review experience that most developers are treating as a minor feature. It is not minor.
You can now take a PR from creation to merge entirely within Cursor. The agent reviews the changes, flags issues, suggests improvements, and tracks the full lifecycle of the PR without you switching to GitHub, back to the terminal, back to GitHub, back to the editor.
The context switching tax in code review is enormous and almost completely invisible because it has always been there. Every time you leave the editor to check a PR comment and come back, you pay a cost. Cursor 3 eliminates that context switch.
The Bugbot integration makes this sharper. With the high effort setting — which you can now customize per team or per individual — Bugbot finds significantly more bugs per run than default. The tradeoff is cost and time. But for critical PRs where a missed bug is expensive, the option to dial up the effort is genuinely useful and not something most PR review tools give you control over.
3. Parallel Agents on Plans — The Feature That Changes How You Scope Work
When you create a plan in Cursor 3, the agents execute steps in parallel where dependencies allow. This sounds like a performance improvement. It is actually a workflow change.
Because steps run in parallel, you start thinking about work differently. Instead of a linear sequence of tasks, you think about the dependency graph. What needs to be done before what? What can happen simultaneously?
This is how senior engineers think about complex work. Cursor 3 essentially externalizes that mental model into the tool. You write the plan. The tool figures out what can run in parallel. You watch multiple things get built at once.
The quick action pills that shipped alongside this — common workflow actions surfaced as one click options rather than typed commands — reduce the friction of directing parallel work significantly. Less typing, faster iteration, more time watching things actually happen.
4. Composer 2 Is the Real Engine — And Most Developers Do Not Understand What It Is
Cursor 3 gets the attention. Composer 2, which shipped on March 19 and powers Cursor 3's agents, is the part that actually explains why the agents feel different.
Composer 2 is not a wrapper around a frontier model. It is Cursor's own model — built on Kimi K2.5 from Moonshot AI as a base, then continued pre-training on a code heavy data mix, followed by large scale reinforcement learning in realistic Cursor sessions. Around 75 percent of the total compute came from Cursor's own training, not the base model.
What this means in practice is that Composer 2 has been trained on how developers actually use Cursor — not just on code in the abstract. It knows the tool it is running in. It understands the workflows. It has been reinforced on real Cursor sessions.
This is a fundamentally different approach from routing your requests to Claude or GPT and hoping the model understands your IDE context. Composer 2 was built for this environment specifically. The capability jump on complex multi-file tasks is noticeable — and it is not placebo.
5. Environment Version History — The Underrated Safety Net
This one shipped quietly in the most recent update and I have not seen anyone write about it yet.
Every development environment in Cursor now has its own version history that you can review and roll back. If an agent configures your environment incorrectly — installs the wrong dependency version, misconfigures a tool, breaks something in the setup — you can roll back to a previous environment state rather than debugging what changed.
For solo developers and small teams this is genuinely useful. Environment configuration bugs are some of the most time consuming to diagnose because the symptoms appear in your code but the cause is in your setup. Version history on the environment itself gives you a direct path back to a known good state.
Admins can also restrict rollback permissions to admins only — which matters for teams where environment consistency is critical and you do not want individual developers rolling back shared configurations without oversight.
The Feature I Am Still Watching
Cursor is rolling out automated environment configuration in private beta for Enterprise teams — where it inspects your repos, figures out the tools and dependencies required, and produces a configuration you can edit and version. As it configures your environment, it asks questions, flags missing credentials, and validates that your environment is set up properly.
This is not widely available yet. But if it works as described it solves one of the most painful parts of onboarding new developers or spinning up new projects — the environment setup that always takes longer than anyone planned and breaks in ways that are specific to the machine, not the code.
What Cursor 3 Actually Is
The announcement framed Cursor 3 as a unified workspace for building software with agents. That is accurate but understates the shift.
The traditional IDE view still exists and still works. You can switch back at any time. But the Agents Window represents a genuinely different model of how software gets built — you as the architect directing agents, not you as the typist writing every line.
The Agents Window, parallel execution, cloud agent handoff, Design Mode, and built-in Git are all meaningful additions that move Cursor from a smart IDE with AI toward something closer to an agent orchestration platform that happens to have an excellent IDE inside it. exactsolution
The features nobody is talking about are the ones that make that shift feel real in daily use rather than just impressive in a demo. Design Mode, PR review lifecycle, environment version history, parallel plan execution — these are the features that change Tuesday afternoon, not just the ones that change the keynote slide.
Exact Solution is a certified refurbished electronics marketplace shipping across Europe. We stock the best refurbished laptops from Apple, Dell, HP, and Lenovo — all fully tested and ready to ship.
Top comments (0)