Runbooks and Work Modes

Runbooks and work modes control different parts of a launch.

Runbooks

runbook controls collaboration depth and coordination limits. It does not choose the model.

Runbook	Use it for
`lite`	Focused, low-overhead work. This is the default.
`heavy`	Longer multi-actor work where intermediate synthesis matters.

lite does not mean a smaller model, and heavy does not mean a bigger model. Model choice is a separate launch field and is still checked by backend preflight.

Work modes

work_mode controls goal posture. It does not choose the provider.

Work mode	Use it for
`directed_effort`	Scoped, outcome-directed execution with a clear target.
`open_ended_discovery`	Exploratory work where discovery and option-finding matter.

Example

run = client.research.runs.start(
    "Explore likely causes of flaky benchmark results and summarize evidence.",
    host_kind="daytona",
    work_mode="open_ended_discovery",
    providers=[{"provider": "openrouter"}],
    runbook="heavy",
)

Backend preflight validates the final launch.

Models and Harnesses Providers and Credentials

⌘I

Getting Started

Managed Research

Stack

Research Factory

Prompt Optimization

Infrastructure

SDK Reference

Research API

Reference

Cookbooks

Runbooks and Work Modes

Runbooks

Work modes

Example

​Runbooks

​Work modes

​Example

Runbooks

Work modes

Example