Runtime economics

Top-model intelligence belongs where it matters most.

AI coding spend grows when every phase uses the same expensive worker. Orcho makes runtime choice explicit: plan with strong reasoning, route bounded implementation and repair through cost-efficient compatible workers, keep review independent, and inspect the result by phase.

PUBLIC ALPHA

Read the technical guide Explore workflow portability

plan accepted

validate_plan accepted

implement evidence open

review_changes findings open

repair_changes queued

final_acceptance awaiting signoff

Policy

Route by phase instead of defaulting by habit.

Planning, implementation, review, repair and final acceptance do not need the same worker. Orcho records the runtime and model behind each phase so a team can make that choice deliberately.

Use strongest reasoning for ambiguous planning and final judgment.
Use compatible lower-cost workers for bounded implementation and repair.
Keep each phase label visible in the run timeline and artifacts.

Supervision

Cost control cannot erase the review boundary.

Runtime economics only works when quality gates still control the run. A cheaper implementation phase should be followed by an independent review or final acceptance phase that can reject, request repair or pause for a human verdict.

Measurement

The tradeoff should be visible after the run.

The evidence bundle and cost accounting surfaces let teams compare runtime mix, retries, findings, token usage and acceptance outcomes. The point is not cheapest possible output; it is a delivery loop with measurable economics.