Quickstart
1. Install mashin
# macOSbrew install mashin-live/tap/mashin
# Or download directlycurl -fsSL https://get.mashin.live | sh2. Create a machine
mashin new classifierThis creates classifier.mashin:
machine classifier
accepts text as text, is required
responds with category as text confidence as number
implements ask classify, using: "anthropic:claude-sonnet-4-6" with task "Classify this text into a category. Return the category name and a confidence score between 0 and 1." returns category as text confidence as number assuming category: "general" confidence: 0.853. Run it
mashin run classifier.mashin --input '{"text": "The quarterly earnings exceeded expectations"}'Output:
{ "category": "finance", "confidence": 0.92}4. Test it (without an API key)
The assuming block provides mock values for testing. Run in test mode:
mashin test classifier.mashinOutput:
classifier classify: category="general", confidence=0.85 (mocked)
1 test, 1 passed, 0 failedNo API key needed. Tests are fast, free, and deterministic.
5. See the governance trace
mashin run classifier.mashin --input '{"text": "hello"}' --traceThe trace shows every governance decision: what permissions were checked, what the LLM was asked, how many tokens it used, and the hash chain proving the execution was not tampered with.
What’s next?
- Key Concepts - Understand machines, steps, and governance
- Platform Overview - How all the platform components fit together
- Introduction to mashin - Full 10-lesson course
- Language Reference - Every keyword documented