A worked example: the loop with the real surfaces

1. 1Plan before you build (Plan modeA mode that makes no edits: it researches the codebase and produces an editable plan you review before any code changes. Press Enter for the full definition.). Run Plan mode before you scaffold. It researches the whole indexed codebase, follows existing paradigms and outputs an editable, hyperlinked Markdown plan with scope, implementation, tests and to-dos. Editing that plan costs zero tokens because it's just Markdown, so you tighten scope for free before a single line is written.
2. 2Let the plan catch the gaps. Plan modeA mode that makes no edits: it researches the codebase and produces an editable plan you review before any code changes. Press Enter for the full definition. asks the scope questions you'd otherwise discover at hour five: single column or summary cards, does the list need search and sort. It also pauses on contradictions. In one workshop the PRDProduct Requirements Document. The spec describing what to build, for whom and why, before implementation starts. Increasingly the artifact you hand an AI agent as the source of truth for a feature. Press Enter for the full definition. said 'use authenticated users' but the agent saw no auth in the app and asked how to handle the gap: build full auth now, or ship a local-first V1. That clarifying question saves you the rework.
3. 3Execute cheap. Plan with a thinking modelA reasoning model (shown with a brain icon in Cursor's picker) that spends extra compute before answering; reach for it on complex, nuanced work and a standard model for fast, simple tasks. Press Enter for the full definition., since planning is all reasoning, then hand the to-dos to Composer 2.5The current Composer release, better at long-running tasks and at judging when a job needs a light touch versus deep work. Press Enter for the full definition.. Composer 2.5 is Cursor's own coding model: it draws from the plan's weekly pool and lists at $0.5 in / $2.5 out per million tokens, a fraction of a frontier model's rate. Third-party models bill at API list price and come only with Premium and above, so on a plan without them, pick the strongest of Cursor's own models for the planning pass. Letting the expensive model write every line burns your budget before the demo.
4. 4Verify visually in the built-in browser. Cursor ships a full browser inside the editor that renders your running app. Give it a plain-language directive, such as 'increase the padding of the heading on the overview page', and watch it render while Cursor edits only the files it needs. Agents can self-test here too, clicking around and taking screenshots.
5. 5Tweak by clicking (Design mode). Design mode lets you target a UI element directly in that browser instead of describing where to look, which also saves the agent from burning tokens searching the DOM. Select a palette and say 'adhere to proper contrast ratios,' or 'lowercase this and give it rounded corners.'

Ship from the flow of workasync, over Slack, human-in-the-loop

The prototype loop isn't confined to the editor. Cursor connects to Slack, and PMs make changes from a thread without opening the IDE at all. One worked case: there were no docs for an AWS Bedrock integration. The PM dropped that into Slack, Cursor read the code and wrote the docs, an engineer replied in-thread flagging two things that were wrong, Cursor was told over the same thread to fix them, and it shipped. The whole loop took about 15 minutes, entirely in Slack.