Sequential Crew
The Sequential Crew component runs a team of AI agents that works like a chain: each task is done by the agent you assigned to it, in the order you set, and each step can build on what the previous ones did. At the end it returns the result of the last task.
Use it when the work always follows the same steps and you know which specialist does each one.
When to use it
- Research a topic, write a text and review it, always in that order.
- Extract data from a document, analyse it and prepare a summary for management.
- Draft a reply to a customer and pass it through a tone reviewer before sending it.
- Turn meeting notes into minutes and then into a list of actions.
Configuration
| Connection | What to connect |
|---|---|
| Tasks | The team’s tasks, chained in order. Connect the last one of the chain of Sequential Task or Sequential Task Agent: it brings the previous ones with it. |
The team’s agents are the ones assigned to the tasks, so you do not need to connect them separately.
Advanced options
| Field | What it does |
|---|---|
| Memory | The team keeps a shared memory across tasks. Default: off. |
| Cache | Reuses a tool’s result when it is asked exactly the same thing again. Default: on. |
| Max RPM | Maximum number of requests per minute the team makes to the AI model. Default: 100. |
| Verbose | Level of detail of the execution record. Default: 0. |
| Share Crew | Shares information about the team’s run with the CrewAI service. Default: off. Leave it off. |
| Function Calling LLM | Connection for an AI model the agents use to call their tools. If you connect nothing, each agent uses its own. |
Output
Output: the text with the team’s final result. Connect it to a Chat Output to show it, or to any component that takes text.
Example
The agency Marea Comunicación prepares press releases. It defines three chained tasks: a researcher agent gathers the facts about a client’s launch, a writer drafts the press release and a reviewer polishes the style. It connects the third task to Tasks of the Sequential Crew and the result to a Chat Output: the release arrives already reviewed.