Cursor · Module 04 of 6

Hidden Features

Capabilities most people miss — Rules, Agents, and Indexing.

3 lessons3 exercises
Topics & techniques

Rules

Persistent project rules that steer every edit.

1 card →
Best practice
Write Rules That Encode Your Conventions
Rules are persistent instructions Cursor applies to its AI edits — project-wide conventions the model should follow every time, stored in your repo so the whole team shares them.
L3 · Workflows

Agents

Background agents that work while you keep coding.

1 card →
Workflow
Hand Off Scoped Tasks to Background Agents
A workflow for Cursor's agents: give a well-scoped task with clear done-criteria and let the agent plan, edit across files, and run commands — while you review the result as a diff.
L4 · Multi-AI systems

Indexing

How Cursor reads your codebase — and how to help it.

1 card →
Knowledge card
Help Cursor Index Your Codebase Well
Indexing is how Cursor builds a searchable map of your repo so it can retrieve relevant files as context. This card is about making that index accurate instead of noisy.
L3 · Workflows
Cursor hidden features

The features that do the heavy lifting

Cursor's real power is not the chat box — it is the features that give the AI context about your project. Rules are persistent instructions applied to every request: your stack, conventions, and the patterns you want or want banned. Indexing builds a searchable map of your codebase so the AI can find the right files on its own. And agents take a goal and execute multi-file changes. Together these are why Cursor understands a project a general assistant never could.

Set them up once, benefit every session

These features reward a little upfront investment. Write real rules and you stop re-explaining your project in every prompt; the AI produces code that matches what already exists. Keep the index fresh and the agent stops missing relevant files. Learn how the agents actually decide what to touch and you supervise them better. The most common reason Cursor underperforms is thin context here — no rules, a stale index — not a weak model.

The hidden-feature topics to explore

This section covers rules, agents, and indexing — the context foundation that makes Cursor work. Pick the card below and set these up properly; the quality jump is immediate.

Frequently asked
What are Cursor rules?

Rules are persistent instructions Cursor applies to every AI request — your stack, conventions, preferred patterns, and things to avoid. They stop you re-explaining your project each time and keep generated code consistent with your codebase.

What is Cursor's codebase indexing?

Indexing builds a searchable map of your project so Cursor's AI can find and pull in the right files on its own, rather than only seeing what you paste. Keeping the index fresh is key to accurate, project-aware edits.

Why is Cursor underperforming for me?

Most often it is thin context, not the model — missing or vague rules, a stale index, or prompts that never point at the relevant files. Setting up rules and indexing properly usually resolves it.

How do Cursor agents decide what to change?

Agents plan from the goal you give plus the project context available to them through indexing and rules. The clearer your brief and the fresher your context, the more accurately they scope what to touch.

Test yourself

Do you know Cursor's hidden features?

Five questions on Rules, background agents, and indexing — the parts of Cursor that quietly decide whether it fits your project or fights it. No sign-up, instant score, and you can share how you did.

  1. Q1 What are Cursor Rules?
  2. Q2 Which rule is actually useful?
  3. Q3 What does a background agent need to stay on the rails?
  4. Q4 What is indexing, and why does it matter?
  5. Q5 You ask a whole-monorepo question when you actually mean one package. What's the cost?
0 / 5 answered