Repeat

Overview#

Run an internal workflow a fixed number of times.

Use this block when its responsibility is clear in the graph. Give it a name that describes the work it performs, then test it with representative input before publishing.

Working examples#

These are complete starting points, not decorative diagrams. Every graph is also available in the main template library and is checked by the workflow compiler.

1. Create three headline options#

You will build: Three independent headline candidates.

Repeated generation gives an editor real choice. Sequential execution and fail-fast behavior make failures obvious.

Open this template and adapt the labels, prompts, or credentials to your own workflow.

2. Generate five ad angles#

You will build: Five distinct campaign angles.

Creates a bounded batch without duplicating blocks manually. The fixed count caps cost before the run starts.

Open this template and adapt the labels, prompts, or credentials to your own workflow.

3. Draft a weekly idea set#

You will build: One idea for each day of the week.

Turns one theme into a predictable planning batch. Collect-all returns every successful iteration in order.

Open this template and adapt the labels, prompts, or credentials to your own workflow.

Ports#

• Input: Input (source): any, optional, single.
• Output: Result (result): any, optional, single.

Inspector#

• Number of times: key count; number; range: 1 to 1000; default: 3.
• If one run fails: key failurePolicy; select; options: fail_fast, continue; default: "fail_fast".
• Runs at once: key concurrency; number; range: 1 to 8; default: 1.
• Return: key resultPolicy; select; options: collect-all, last; default: "collect-all".
• nested-workflow editor: manages body with edit, validate, preview support.

Behavior#

• Input requirement: No inbound value is required by the contract.
• Execution: Handled by the orchestrator using repeat.
• Timeout: No node-level timeout is defined.

Cost#

Uses workflow compute and may contribute to the run's compute cost.

Security#

• No credentials are used.
• The node has no external side effects.

Retry#

Retry and resume behavior is owned by the workflow orchestrator rather than a nested node retry loop.

Production checklist#

• Test the happy path and one malformed or empty input.
• Keep credentials out of prompts and published graph configuration.
• Set a timeout and retry policy that matches the operation's side effects.
• Name the final result so a runner can tell what success looks like.