A convention-oriented framework for creating structured AI workflows, maintained by the Augmented Engineering team at Shopify.
Roast provides a structured, declarative approach to building AI workflows with:
- Convention over configuration: Define powerful workflows using simple YAML configuration files and prompts written in markdown (with ERB support)
- Built-in tools: Ready-to-use tools for file operations, search, and AI interactions
- Ruby integration: When prompts aren't enough, write custom steps in Ruby using a clean, extensible architecture
- Shared context: Each step shares its conversation transcript with its parent workflow by default
- Step customization: Steps can be fully configured with their own AI models and parameters.
- Session replay: Rerun previous sessions starting at a specified step to speed up development time
- Parallel execution: Run multiple steps concurrently to speed up workflow execution
- Function caching: Flexibly cache the results of tool function calls to speed up workflows
- Extensive instrumentation: Monitor and track workflow execution, AI calls, and tool usage (see instrumentation documentation)
Here's a simple workflow that analyzes test files:
name: analyze_tests
# Default model for all steps
model: gpt-4o-mini
tools:
- Roast::Tools::ReadFile
- Roast::Tools::Grep
steps:
- read_test_file
- analyze_coverage
- generate_report
# Step-specific model overrides the global model
analyze_coverage:
model: gpt-4-turbo
json: trueEach step can have its own prompt file (e.g., analyze_coverage/prompt.md) and configuration. Steps can be run in parallel by nesting them in arrays:
steps:
- prepare_data
-
- analyze_code_quality
- check_test_coverage
- verify_documentation
- generate_final_reportWorkflows can include steps that run bash commands (wrap in $()), use interpolation with {{}} syntax, and even simple inlined prompts as a natural language string.
steps:
- analyze_spec
- create_minitest
- run_and_improve
- $(bundle exec rubocop -A {{file}})
- Summarize the changes made to {{File.basename(file)}}.- Create a workflow YAML file defining your steps and tools
- Create prompt files for each step (e.g.,
step_name/prompt.md) - Run the workflow:
# With a target file
roast execute workflow.yml target_file.rb
# Or for a targetless workflow (API calls, data generation, etc.)
roast execute workflow.ymlIn Roast, workflows maintain a single conversation with the AI model throughout execution. Each step represents one or more user-assistant interactions within this conversation, with optional tool calls. Steps naturally build upon each other through the shared context.
Roast supports several types of steps:
- Standard step: References a directory containing at least a
prompt.mdand optionaloutput.txttemplate. This is the most common type of step.
steps:
- analyze_codeAs an alternative to a directory, you can also implement a custom step as a Ruby class, optionally extending Roast::Workflow::BaseStep.
In the example given above, the script would live at workflow/analyze_code.rb and should contain a class named AnalyzeCode with an initializer that takes a workflow object as context, and a call method that will be invoked to run the step. The result of the call method will be stored in the workflow.output hash.
-
Parallel steps: Groups of steps executed concurrently
steps: - - analyze_code_quality - check_test_coverage
-
Command execution step: Executes shell commands directly, just wrap in
$(expr)steps: - $(command line expr) - rubocop: $(bundle exec rubocop -A)
This will execute the command and store the result in the workflow output hash. Explicit key name is optional (
rubocopin the second line of the example). -
Raw prompt step: Simple text prompts for the model without tools
steps: - Summarize the changes made to the codebase.
This creates a simple prompt-response interaction without tool calls or looping. It's detected by the presence of spaces in the step name and is useful for summarization or simple questions at the end of a workflow.
Roast handles data flow between steps in three primary ways:
-
Conversation Context (Implicit): The LLM naturally remembers the entire conversation history, including all previous prompts and responses. In most cases, this is all you need for a step to reference and build upon previous results. This is the preferred approach for most prompt-oriented workflows.
-
Output Hash (Explicit): Each step's result is automatically stored in the
workflow.outputhash using the step name as the key. This programmatic access is mainly useful when:- You need to perform non-LLM transformations on data
- You're writing custom output logic
- You need to access specific values for presentation or logging
-
Interpolation (Dynamic): You can use
{{expression}}syntax to inject values from the workflow context directly into step names, commands, or prompt text. For example:steps: - analyze_file - $(rubocop -A {{file}}) - Generate a summary for {{file}} - result_for_{{file}}: store_results
Interpolation supports:
- Simple variable access:
{{file}},{{resource.target}} - Access to step outputs:
{{output['previous_step']}} - Any valid Ruby expression evaluated in the workflow context:
{{File.basename(file)}}
- Simple variable access:
For typical AI workflows, the continuous conversation history provides seamless data flow without requiring explicit access to the output hash. Steps can simply refer to previous information in their prompts, and the AI model will use its memory of the conversation to provide context-aware responses. For more dynamic requirements, the interpolation syntax provides a convenient way to inject context-specific values into steps.
-o, --output FILE: Save results to a file instead of outputting to STDOUT-c, --concise: Use concise output templates (exposed as a boolean flag onworkflow)-v, --verbose: Show output from all steps as they execute-r, --replay STEP_NAME: Resume a workflow from a specific step, optionally with a specific session timestamp
The session replay feature allows you to resume workflows from specific steps, saving time during development and debugging:
# Resume from a specific step
roast execute workflow.yml -r step_name
# Resume from a specific step in a specific session
roast execute workflow.yml -r 20250507_123456_789:step_nameSessions are automatically saved during workflow execution. Each step's state, including the conversation transcript and output, is persisted to a session directory. The session directories are organized by workflow name and file, with timestamps for each run.
This feature is particularly useful when:
- Debugging specific steps in a long workflow
- Iterating on prompts without rerunning the entire workflow
- Resuming after failures in long-running workflows
Sessions are stored in the .roast/sessions/ directory in your project. Note that there is no automatic cleanup of session data, so you might want to periodically delete old sessions yourself.
The target option is highly flexible and accepts several formats:
Single file path:
roast execute workflow.yml -t path/to/file.rb
# is equivalent to
roast execute workflow.yml path/to/file.rbDirectory path:
roast execute workflow.yml -t path/to/directory
# Roast will run on the directory as a resourceGlob patterns:
roast execute workflow.yml -t "**/*_test.rb"
# Roast will run the workflow on each matching fileURL as target:
roast execute workflow.yml -t "https://api.example.com/data"
# Roast will run the workflow using the URL as a resourceAPI configuration (Fetch API-style):
roast execute workflow.yml -t '{
"url": "https://api.example.com/resource",
"options": {
"method": "POST",
"headers": {
"Content-Type": "application/json",
"Authorization": "Bearer ${API_TOKEN}"
},
"body": {
"query": "search term",
"limit": 10
}
}
}'
# Roast will recognize this as an API configuration with Fetch API-style formatShell command execution with $(...):
roast execute workflow.yml -t "$(find . -name '*.rb' -mtime -1)"
# Roast will run the workflow on each file returned (expects one per line)Git integration examples:
# Process changed test files
roast execute workflow.yml -t "$(git diff --name-only HEAD | grep _test.rb)"
# Process staged files
roast execute workflow.yml -t "$(git diff --cached --name-only)"Roast also supports workflows that don't operate on a specific pre-defined set of target files:
API-driven workflows:
name: API Integration Workflow
tools:
- Roast::Tools::ReadFile
- Roast::Tools::WriteFile
# Dynamic API token using shell command
api_token: $(cat ~/.my_token)
# Option 1: Use a targetless workflow with API logic in steps
steps:
- fetch_api_data # Step will make API calls
- transform_data
- generate_report
# Option 2: Specify an API target directly in the workflow
target: '{
"url": "https://api.example.com/resource",
"options": {
"method": "GET",
"headers": {
"Authorization": "Bearer ${API_TOKEN}"
}
}
}'
steps:
- process_api_response
- generate_reportData generation workflows:
name: Generate Documentation
tools:
- Roast::Tools::WriteFile
steps:
- generate_outline
- write_documentation
- create_examplesThese targetless workflows are ideal for:
- API integrations
- Content generation
- Report creation
- Interactive tools
- Scheduled automation tasks
You can set a default model for all steps in your workflow by specifying the model parameter at the top level:
name: My Workflow
model: gpt-4o-mini # Will be used for all steps unless overriddenIndividual steps can override this setting with their own model parameter:
analyze_data:
model: anthropic:claude-3-haiku # Takes precedence over the global modelRoast allows you to dynamically fetch API tokens using shell commands directly in your workflow configuration:
# This will execute the shell command and use the result as the API token
api_token: $(print-token --key)
# Or a simpler example for demonstration:
api_token: $(echo $OPENAI_API_KEY)This makes it easy to use environment-specific tokens without hardcoding credentials, especially useful in development environments or CI/CD pipelines.
Each step can have an output.txt file that uses ERB templating to format the final output. This allows you to customize how the AI's response is processed and displayed.
Example step_name/output.txt:
<% if workflow.verbose %>
Detailed Analysis:
<%= response %>
<% else %>
Summary: <%= response.lines.first %>
<% end %>
Files analyzed: <%= workflow.file %>
Status: <%= workflow.output['status'] || 'completed' %>This is an example of where the workflow.output hash is useful - formatting output for display based on data from previous steps.
Available in templates:
response: The AI's response for this stepworkflow: Access to the workflow objectworkflow.output: The shared hash containing results from all steps when you need programmatic accessworkflow.file: Current file being processed (ornilfor targetless workflows)- All workflow configuration options
For most workflows, you'll mainly use response to access the current step's results. The workflow.output hash becomes valuable when you need to reference specific data points from previous steps in your templates or for conditional display logic.
Roast provides extensive instrumentation capabilities using ActiveSupport::Notifications. You can monitor workflow execution, track AI model usage, measure performance, and integrate with external monitoring systems. Read the full instrumentation documentation.
You can create your own tools using the Raix function dispatch pattern. Custom tools should be placed in .roast/initializers/ (subdirectories are supported):
# .roast/initializers/tools/git_analyzer.rb
module MyProject
module Tools
module GitAnalyzer
extend self
def self.included(base)
base.class_eval do
function(
:analyze_commit,
"Analyze a git commit for code quality and changes",
commit_sha: { type: "string", description: "The SHA of the commit to analyze" },
include_diff: { type: "boolean", description: "Include the full diff in the analysis", default: false }
) do |params|
GitAnalyzer.call(params[:commit_sha], params[:include_diff])
end
end
end
def call(commit_sha, include_diff = false)
Roast::Helpers::Logger.info("🔍 Analyzing commit: #{commit_sha}\n")
# Your implementation here
commit_info = `git show #{commit_sha} --stat`
commit_info += "\n\n" + `git show #{commit_sha}` if include_diff
commit_info
rescue StandardError => e
"Error analyzing commit: #{e.message}".tap do |error_message|
Roast::Helpers::Logger.error(error_message + "\n")
end
end
end
end
endThen include your tool in the workflow:
tools:
- MyProject::Tools::GitAnalyzerThe tool will be available to the AI model during workflow execution, and it can call analyze_commit with the appropriate parameters.
You can extend Roast with project-specific configuration by creating initializers in .roast/initializers/. These are automatically loaded when workflows run, allowing you to:
- Add custom instrumentation
- Configure monitoring and metrics
- Set up project-specific tools
- Customize workflow behavior
Example structure:
your-project/
├── .roast/
│ └── initializers/
│ ├── metrics.rb
│ ├── logging.rb
│ └── custom_tools.rb
└── ...
$ gem install roast-aiOr add to your Gemfile:
gem 'roast-ai'After checking out the repo, run bundle install to install dependencies. Then, run bundle exec rake to run the tests and linter. You can also run bin/console for an interactive prompt that will allow you to experiment.
The gem is available as open source under the terms of the MIT License.