Skip to main content
Dundie·Feature Parity Map← all products

cursor capabilities

9 mapped capabilities, each graded and dated. This is the diagnosis — the migration guide is the cure.


Capabilities

Agents, Composer, Bugbot and Cloud Agents

provisionalverified 4 days ago

Cursor's agentic surface includes the in-editor Agent mode (Composer), background/Cloud Agents that run on Anysphere VMs, Bugbot automated PR review, and Automations (scheduled or event-driven agents). Cursor 2.0 added parallel multi-agent execution (up to 8 agents on the same task via git worktrees, picking the best result).

low confidence · 0.55docssource ↗source ↗

File editing (multi-file edits, diffs, undo)

provisionalverified 4 days ago

Cursor edits one or many files in a single agent turn, presenting changes as inline diffs that the developer accepts or rejects per hunk or per file. The inline Cmd+K prompt edits a selection or empty buffer; Composer/Agent edits across many files at once.

low confidence · 0.20docssource ↗source ↗

IDE / editor (VS Code fork)

provisionalverified 4 days ago

Cursor is a standalone desktop IDE built as a fork of VS Code (Code OSS). It ships full editor functionality (file tree, terminals, debugger, source control) with AI features layered throughout, and is generally compatible with the VS Code extension ecosystem via Open VSX and direct VSIX install.

low confidence · 0.55docssource ↗source ↗

In-editor chat (Agents Window)

provisionalverified 4 days ago

Conversational AI panel for asking questions about code, generating new code, and running multi-step agent tasks. Since Cursor 2.0 (Oct 2025) and Cursor 3.0, the historic Chat / Composer / Cmd+L panes were unified into an agent-centric 'Agents Window' that hosts chat, agents, PR review tabs, browsers, and terminals.

low confidence · 0.20docssource ↗source ↗

Model choice and bring-your-own-key

provisionalverified 4 days ago

Cursor offers a model picker with multiple frontier models from Anthropic, OpenAI, Google, xAI, plus its in-house Composer family. Auto mode routes requests to a suitable model and does not draw from the per-plan credit pool; manually picking a frontier model debits credits.

low confidence · 0.55docssource ↗source ↗

Plan and pricing gating

provisionalverified 4 days ago

Six self-serve tiers (Hobby, Pro, Pro+, Ultra, Teams, Enterprise). Since June 2025, paid plans bundle a monthly credit pool equal to the subscription price; manually picking a frontier model debits credits while Auto mode is unlimited. On-demand usage continues past the included pool, billed in arrears.

low confidence · 0.55docssource ↗source ↗

Repo context and indexing (@-symbols)

provisionalverified 4 days ago

Cursor automatically builds a semantic index of the open workspace (AST-aware embeddings) and exposes explicit context controls through @-mentions. The agent also performs agentic / semantic search at query time to pull in relevant files.

low confidence · 0.20docssource ↗source ↗

Tab autocomplete (inline + multi-line)

provisionalverified 4 days ago

Cursor Tab is Anysphere's proprietary next-action prediction model offering inline single-token, multi-line, and cross-file edit suggestions. It anticipates the developer's next change (refactors, ripple edits) rather than only completing the current line.

low confidence · 0.55docssource ↗source ↗

Terminal access and AI terminal commands

provisionalverified 4 days ago

Cursor embeds the standard VS Code integrated terminal and adds an AI prompt for generating shell commands from natural language. The Agent / Composer can also execute terminal commands as part of multi-step tasks (with approval prompts unless YOLO/auto-run is enabled).

low confidence · 0.20docssource ↗source ↗

Editorial guidance, not a warranty. AI tools change weekly; every entry carries the date it was last verified. Verify before relying on a specific capability.