Lesson 9: Interpretation Modes

Your email triage is live, tested, and learning. Your manager asks: “What exactly does this thing do? How much does it cost? Is it compliant with our data handling policy?”

You could explain it yourself. Or you could ask mashin to analyze the machine and answer those questions directly.

Six Ways to Analyze a Machine

Type any of these in Koda:

/explain email_triage

You see a structured description: what the machine does step by step, what inputs it needs, what it outputs, what external systems it touches, what models it uses.

No need to read the code. The explanation is generated from the machine’s structure.

/cost email_triage

You see:

Estimated cost per run: $0.0003
  classify: claude-haiku-4, ~200 tokens, $0.0003
  route: decide (no cost)
  notify/task: effect machine (no AI cost)

At 150 runs/day: $0.045/day, $1.35/month

The cost estimate walks through every step, identifies which ones call AI models, looks up current pricing, and projects daily and monthly costs.

/simulate email_triage

Runs the machine with mocked effects. The AI steps return synthetic responses from your test cases. The Teams and Planner calls are simulated. You see the full execution flow without actually sending messages or creating tasks.

/evaluate email_triage

Runs the machine against all its verifies test cases and reports:

4/4 tests passed
Accuracy: 100%
Average confidence: 0.85

/verify email_triage

Runs a governance compliance check:

[pass] Valid structure
[pass] Capabilities declared
[pass] Models on allowlist
[pass] Step count within limits
[pass] Governance sections present
[pass] Derivation trust verified

This is the same check that runs before any machine is promoted to production. You can run it yourself anytime.

/improve email_triage

Proposes improvements: better prompts, missing edge cases, cost optimizations. Returns a diff showing what would change, without changing anything.

Using Modes in Code

Interpretation modes are not just slash commands. You can use them in machines:

machine pre_deploy_check

accepts
  machine_name as text, is required

responds with
  ready as boolean
  blockers as list

implements
  ask governance, from: email_triage, to: verify
  ask costs, from: email_triage, to: cost
  ask quality, from: email_triage, to: evaluate

  compute assess
    {
      let blockers = []
      let blockers = if (governance.is_compliant is not true) { [...blockers, "governance check failed"] } else { blockers }
      let blockers = if (costs.total_estimated_cost > 0.50) { [...blockers, "cost exceeds $0.50/run"] } else { blockers }
      let blockers = if (quality.accuracy < 0.9) { [...blockers, "accuracy below 90%"] } else { blockers }
      {ready: blockers.length == 0, blockers: blockers}
    }

ask governance, from: email_triage, to: verify interprets the machine in verify mode. The to: modifier tells the runtime to analyze instead of execute.

This machine checks governance, cost, and quality automatically before any deployment.

Custom Modes

The six built-in modes cover common needs. For specialized analysis, write your own:

machine compliance_auditor

accepts
  target_form as text, is required
  target_name as text
  standard as text, default: "internal"

responds with
  compliant as boolean
  findings as list

implements
  ask audit, using: "anthropic:claude-sonnet-4"
    with role "You are a compliance auditor for AI systems."
    with task "Check this machine against ${input.standard} compliance standards.\n\nMachine: ${input.target_form}"
    returns
      compliant as boolean
      findings as list

Use it as a custom interpretation mode:

ask audit_result, from: email_triage, to: compliance_auditor
  standard: "EU AI Act"

The runtime passes your triage machine’s form and name to the auditor. The auditor analyzes it against the standard you specified.

The Bigger Picture

Interpretation modes exist because machines are structured data, not opaque code. The system can walk through a machine’s steps, read its models, check its governance, estimate its costs. All without running it.

This is what it means to have a governed platform: you can understand, audit, and verify any machine at any time.

What Comes Next

You have built, deployed, tested, and analyzed an email triage system. The final lesson goes deeper: how machines can inspect and improve themselves. Metaprogramming: the machine as a value that can be transformed.

Next: Metaprogramming →