create_campaign
Create a new campaign to manage long-running, multi-step AI agent workflows. Define goal, priority, and optional success metrics to track progress.
Instructions
Create a new campaign for long-running, multi-step work.
Args:
goal: What this campaign should accomplish.
name: Short name for display. Auto-generated if omitted.
channel: Discord channel for notifications.
priority: urgent / high / normal / low / background.
max_depth: Max nesting depth for subtasks (default 4).
token_budget: Optional token limit. NULL = unlimited.
dry_run: If true, create in paused status for review.
success_metric: Short metric name emitted by the verifier /
benchmark (e.g. "accuracy_at_1k"). Paired with
benchmark_command. Leave NULL for free-form campaigns.
benchmark_command: Shell / Python invocation that produces a
JSON line with the metric value. Metadata only — the
runner does not execute it; worker steps do.
scope: Freeform identifier narrowing the benchmark
(e.g. "chapter-01", "test_subset_A").
max_iterations: Hard cap on autoresearch-style loops. NULL
means open-ended (planner decides).
Returns: Campaign ID, name, status, next_action_at.
Next: Use get_campaign(id) to check progress, or steer_campaign(id, guidance) to adjust.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | ||
| name | No | ||
| channel | No | ||
| priority | No | normal | |
| max_depth | No | ||
| token_budget | No | ||
| dry_run | No | ||
| success_metric | No | ||
| benchmark_command | No | ||
| scope | No | ||
| max_iterations | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||