AI crews allow you to use entire teams of AI agents to perform complex tasks. It may initially seem confusing, but the Crew approach simply copies how real teams work. In any given team, you’ll have individuals with unique roles and skills, working together to reach a common goal.
Let’s say you want to create and publish a long-form blog post. The work usually starts with an SEO specialist researching keywords and outlining the content. They’ll create an SEO brief, which will be passed on to the content writer. Once the writer is done, their colleague will proofread and edit the article to ensure quality. What about the featured images or infographics? A designer will help with that.
You already have at least three or four people working on creating this piece of content. They share a common goal, but each specializes in something else and performs a different subtask. Let’s see how you can copy this team as a group of AI agents.
Curious about the Flow we’re analyzing in this guide? It’s the Advanced Blog Generator and you can easily find it in your Flow library.
What Is The Sequential Crew Component?
The Sequential Crew component represents a group of agents that execute tasks in an exact order. It’s essentially a way to tell agents that they’re a team. There may be more than one independent team within your Flow, meaning more than one Sequential Crew component distinguishing these teams from each other.
How Are Crews Better Than Single Agents?
If there’s an issue in your team’s processes, you can quickly pinpoint the issue and work with the competent team member to find a solution. Now imagine it’s just you working on the entire task, and the issue arises in your own mind. That’s much harder to pinpoint and even harder to resolve. The same happens when comparing a single agent with a crew of agents.
When prompting a single agent, you give it the main task with little to no control over how individual subtasks are performed. Complex tasks can easily lead to bottlenecks and low output quality.
On the other hand, crews allow you to split the main task into specific subtasks, assigning each to a unique AI team member. The result is a much more professional and detailed output. It also means easier debugging and handling of much more complex tasks.
The difference between Sequential and SelfManaged Crews
You might have noticed there are two Crew components in your dashboard. The difference between these types of crews is in the order of tasks and the level of control you get.
With a Sequential Crew, the tasks are performed one after another in the exact order you specify. Once a task is done, it’s done and the Flow moves on to the next agent. The sequential approach is great for linear processes that don’t require task repetition.
But this isn’t always the case in the real world. Let’s take a real-life content writer. They will first do research and move on to writing, but as the article unfolds, they may realize more research is needed. Understandably, they will go back and forth between research and writing tasks before finally moving on to the next step. The sequential crew won’t do this. Once a task is done, it’s just done. That’s where Self-Managed crews come in.
With a Self-Managed Crew, the manager AI agent decides the order of tasks. When making decisions, the AI tries to copy traditional organizational hierarchies closely. This opens up the possibility of repeating tasks and creating multiple iterations of the final output.
How to use Sequential Crews
The sequential crew is a structure component that creates a team from AI agents. To use the Sequential Crew component, we need to set up the agents and their tasks first, only then can we bring them together in a crew.
Setting up Sequential Crews consists of three steps:
- Setting up individual AI agents
- Giving agents tasks
- Making the agents a sequential crew
Setting up individual AI agents
Each member of a real team has a role, goals, and a unique backstory that includes their past experiences, personality, and specific style. So does each AI Agent.
For example, let’s focus on the content writer team member:
- The Role is your agent’s job title. In this example, being a content writer is the role.
- The Goal is what the agent does and what their ideal outcome is. The expected outcome for the content writer is a well-written article that adheres to the theme and SEO brief.
- The Backstory is who the agent is. We always bring our personality, way of thinking, vocabulary, and past experiences to anything we do. This is the place where you give your agent these unique characteristics.
Go ahead and set up some agents. When creating a crew, always think of the end goal and which team members would you need to successfully achieve it. Then create agents that represent these team members. You will then give these agents tasks.
In our content writing example, we’ve created the SEO researcher, copywriter and proofreader agents. But the agents and tasks always depend on your specific needs and processes. Feel free to break down the existing process even more or add new agents. For example, you can add a designer agent that will generate images to go along with your article.
Learn more about AI agents and how to use the AI Agent component
Giving Agents Tasks
Continuing with our blog creation example, we now know who our agent is. The next step is to let the agent know their task. Just like in a real team, agents in crews are assigned one or multiple tasks to perform. The task components allow you to define and assign these tasks.
You’ll notice that, like with the crew components, there are two possible task components— sequential and SelfManaged. Since these are two opposite approaches to managing agents, mixing them would make no sense. That’s why we’ll also use sequential tasks when using a sequential crew.
Take the Sequential Task component and connect it to the agent that will perform the task. Below, you can see several agents, each connected to their own task:
In addition to the task, each agent in a Crew can also get appropriate tools, making their job easier and more accurate. In our example, the researcher uses the GoogleSearch and URL Retriever tools to control the research options.
Notice how the tasks are linked. The task component contains the agent’s output. You must connect the tasks to ensure the next agent in line can access the previous agent’s output.
Setting up Sequential Tasks
Each task must have a description, an expected output, and an agent responsible for executing this task. You have already set up specific agents and connected them to task components. Now you need to describe the tasks and tweak the output.
Unsure about how to set up Sequential Tasks? Refer to our guide to learn everything you need to know.
Just to illustrate, a task description for our content writer agent might go a little something like this:
“Given the SEO content brief, write a blog post in no more than 1500 words.
Never start paragraphs with vague statements such as "In the fast-changing field of...". Always go directly to the main information the paragraph should deliver. “
Let’s take a closer look at this task description:
“Given the content brief” - The agent knows what to do with the previous output.
“Write a blog post of up to 1500 words” = The output we expect from the agent.
“Never start…..” = Giving additional custom instructions to tweak the output. These instructions can be any pointers on language, vocabulary, structure or anything else that will help the agent create what you need.The expected output field is optional and works great for when you need a clearly structured output. For example, our SEO researcher agent’s task is to:
A brief in this form:
SEO friendly Title:
SEO friendly Meta description:
SEO friendly OutlineEnsuring it doesn’t forget to start the output with a title and meta description.
Think of the end goal of the complex task the team is meant to achieve. What does each agent have to do to achieve the desired final output? Based on the agents you’ve set up, create one or multiple tasks for each and assign them.
Note: Remember that sequential crews work with sequential tasks only, and SelfManaged crews work with SelfManaged tasks only.
Making The Agents A Crew
Let’s go back to our Flow. It features three agents, each performing their specific task in a clearly defined order—a sequence. The last step of creating a crew is letting the agents know they’re a team. This is where the Sequential Crew component comes into play.
The Sequential Crew Component
The Sequential Crew component represents a group of agents that execute tasks in an exact order. It’s essentially a way to tell agents that they’re a team. There may be more than one independent team within your Flow, meaning more than one Sequential Crew component distinguishing these teams from each other.
The Sequential Crew component is always at the end of the sequence. In our example, we only use one crew, but we still need to bring the agents together with the Sequential Crew:
That’s it. Just send it to output or further processing, and now you have a team of agents working in an exact order. Our Flow includes three agents: an SEO specialist, a content writer, and a proofreader.
Instead of vague output laden with telltale AI phrases, this Flow’s output will be well researched, inspired by top Google results, written according to a clear brief, and edited to avoid sounding like generic AI. Plus, using a group of agents instead of a single agent minimizes bottlenecks. It ensures that any issues can be diagnosed and resolved promptly by simply tweaking one of the agents.
The Flow we used in this guide was the Advanced Blog Generator, which you can find in your Flow library.
