Skip to lesson
Exit
Deep Dive: RL for Coding Agents1 / 2

1 min lesson

Auto Install: a prior model builds the environment

Explain the order in "Auto Install: a prior model builds the environment", then say how you would verify the result.

Step 1 of 2

Auto Install: a prior model builds the environmentComposer 1.5 as the constructor

A coding problem isn't trainable until its repo copy actually builds, installs and runs its tests. Doing that by hand for every environment doesn't scale, so Cursor automates it with the previous model. ComposerCursor's own fast coding model, tuned for the editor and priced well below frontier models; the recommended day-to-day model for executing a plan. Press Enter for the full definition. 1.5 constructs each training environment before Composer 2Cursor's in-house agentic coding model: frontier-level coding quality at high speed and low cost, built as a software-engineering specialist rather than a general-purpose model. Press Enter for the full definition. ever trains in it.

  1. 1Explore. The prior model reads the repo to understand its language, build system and how it's meant to run.
  2. 2Propose setup. It proposes roughly ten install commands to stand the project up from a clean checkout.
  3. 3Write tests. It writes the tests that will serve as the verifiable reward signal for that environment.
  4. 4Install, mock, retry. It runs the install, mocks what it must and retries until the tests actually pass - only then is the environment a usable, gradeable training target.
Why use the old model to build environments

Standing up an arbitrary repo - right dependencies, a working build, runnable tests - is itself a hard agent-driven coding task. Cursor already had a capable coding agent in ComposerCursor's own fast coding model, tuned for the editor and priced well below frontier models; the recommended day-to-day model for executing a plan. Press Enter for the full definition. 1.5, so they pointed it at environment construction: explore, propose the install commands, write tests, then install/mock/retry until green. That turns environment creation from a manual bottleneck into something that scales with compute, which is the whole reason you can train on a large pool of real repos at all.