Rush docs
Send a request.
Get the work back, with proof.
An agent does the work in its own cloud sandbox, with a computer and a browser, and returns a pull request, a report, files or an answer, beside the full record of how it got there.
Three ways in, one API
From your coding agent
Hand Rush a task without leaving Claude Code, Codex or Cursor. Add the MCP server once, or point any agent at the skill, and it starts runs as tool calls.
MCP serverclaude mcp add --transport http rush https://api.phoenix.so/mcp --header "Authorization: Bearer $RUSH_API_KEY"What people send
All 11 use casesReview every pull request
A review on the PR
Each pull request gets an agent that checks it out in its own sandbox, runs the tests and posts a review with the evidence.
Open the recipeFix a bug from an alert
A PR with checks
Your alerting posts to a webhook trigger; an agent reproduces the failure, fixes it and opens a pull request with the checks passing.
Open the recipeRun an agent per customer task
A typed answer, by webhook
Your backend starts one session per customer request with an API key, and Rush posts the result to your webhook when the turn ends.
Open the recipeProduce a report or file, no repo
A file you download
Send a request with no repository; the agent works in its own computer and returns a file as one of the session's artifacts.
Open the recipeWhat comes back
Every run ends with its result beside the record of how it got there: the pull request and its checks, the files it saved, every command it ran and what it cost.
When the proof is missing, the run says so. It ends needs_review, never a false completed.

How it works
Learn
Do it once, start to finish.
Lessons that walk a run from the first request to the pull request, from the console or your own code.