Skip to content
#

Fit RunStory into your workflow

RunStory checks your software by running it. Start that check where it suits the way you work: at each commit, over a span of commits, at each push, or in your pipeline.

#

Where a check can start

Where a RunStory check can start, and what drives it your machine your Git host and pipeline commit commit commit push CI pull request merge release a check starts here driven by Each commit the commit hook CLI A span of commits you or your agent asks CLI one check Each push nothing to install GitHub App once CI passes A pipeline step a job with an API key CLI

Four places to start a check. Three go through the runstory CLI: two on your machine, and one in a pipeline job with an API key. The GitHub App needs no CLI at all.

A check startsDriven byHow
At each commitThe CLI, on your machineTurn it on with runstory settings --automatic on
Over a span of commitsThe CLI, on your machineYou or your coding agent runs runstory run <from>..
At each pushThe GitHub AppConnect the repository and turn on automatic checks. Each push is then checked after CI passes
As a pipeline stepThe CLI, in a jobThe job runs runstory run, signed in with an API key

Wherever it starts, it's the same check. RunStory builds and starts your app from the commit, uses it the way a user would with the latest frontier models, and confirms each failure before it reports it.

#

Find your workflow

#

Why every workflow needs it

Coding agents write code faster than anyone can run it. The checks most teams already have read the code or run its tests.

The checkWhat it tells you
Tests in CIThe cases that have a test still pass
Code review, by a person or a botThe diff reads well
The coding agent's own reportThe agent believes the work is done
RunStoryWhat the app does when someone uses it

Spotify's engineers call one failure of their background coding agents the most serious: a pull request that "passes CI but is functionally incorrect."

However bespoke your software factory is, it needs that last signal somewhere on the line, from something other than the agent that wrote the change. Where it goes depends on how you work.

#

What comes back

A finding goes back to the coding agent and is retested Coding agent main RunStory commits a check starts the finding and its script commits the fix Writes the change Fixes the code as its turn ends Builds and runs the commit agents use the app like a user Confirms each failure 3 more runs and a second agent Retests the script 3 passes close the finding

Every workflow closes the same loop. A confirmed failure goes back to your coding agent with a script that repeats it, the agent commits a fix, and RunStory runs the script again.

WhereWhat you get
Your coding agentEach new finding at the end of its turn, in Claude Code, Codex, and Cursor
Your terminalrunstory status and runstory findings, or JSON for a script
The check's web pageEach finding and its script, plus a video of the browser for a web app
GitHubA Check named Runstory on the commit and its pull request
Your pipelineAn exit code: 0 for no confirmed problems, 1 for a new one
#

Get started

RunStory is in beta for CLIs and web apps, and your first 10 checks are free.

Set up with your agent

Set up runstory for me. Fetch https://runstory.specstory.com/agents.md and follow it. Ask me before spending money. I'll handle sign-in and secrets myself.

Or install it yourself:

  1. Install the CLI on macOS or Linux.

    curl -fsSL https://runstory.specstory.com/install.sh | sh
    
  2. Set up a repository and run your first check. Each command runs only if the one before it worked, so nothing is checked until your app boots.

    runstory init && runstory setup && runstory run
    

For a pipeline, or any machine that runs without you, create an API key on the keys page and store it as the secret RUNSTORY_API_TOKEN.