Remixed Workflow
Compose a pinned workflow as a sealed black box.
Workflow creators.
Overview#
Compose a pinned workflow as a sealed black box.
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. Reuse a vetted legal summarizer#
You will build: A summary produced by a pinned published workflow.
Reuses reviewed logic without exposing or copying its internals. The pinned version keeps behavior stable until you choose to upgrade.
Open this template and adapt the labels, prompts, or credentials to your own workflow.
2. Embed a brand-approved writer#
You will build: Copy produced through a sealed brand workflow.
Lets teams compose approved capabilities safely. Credentials and internal prompts remain owned by the parent workflow.
Open this template and adapt the labels, prompts, or credentials to your own workflow.
3. Compose a research specialist#
You will build: A memo from a pinned specialist workflow.
Adds a maintained research capability as one block. Version pinning prevents silent behavior changes.
Open this template and adapt the labels, prompts, or credentials to your own workflow.
Ports#
- Input: Input (
input):any, optional, single. - Output: Output (
output):any, optional, single. - Dynamic contract: Ports are refined from the pinned
remixContractmetadata.
Inspector#
This node has no direct inspector fields.
Behavior#
- Input requirement: No inbound value is required by the contract.
- Execution: Handled by the orchestrator using
remixed-workflow. - Timeout: No node-level timeout is defined.
Cost#
Cost is inherited from the pinned sealed parent workflow.
Security#
- Credentials remain owned by the sealed parent workflow and are not exposed to the containing workflow.
- The node can create externally visible work as part of its execution.
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.
Was this useful?
Your response helps us improve the documentation.