Overwhelmed by 500 replies in your inbox? Spending days just on negotiations? Let the AI agent handle your creator communications!

The AI agent can automate everything from sending the first message to negotiating terms and making offers.

It works using Quick Actions. You just define the agent's behavior with simple "If this happens, then do that (using a Quick Action)" rules.

Here's how to create your agent:

1. First, create Quick Email Actions for all the tasks you want to automate (like responding to interested bloggers, requesting stats, or declining a collaboration). You can learn more about creating Quick Actions here.
2. Next, go to 'Blogger AI Agent Settings' in your settings.
3. Click the 'Create AI Agent' button.
4. Give the agent a name, specify the stages where it should be active, and select the Quick Actions it will use.
5. Write out the instructions for how the agent should interact with creators.

Here’s an example of an AI agent's workflow:

The blogger's first message is usually a response to our newsletter with an offer of cooperation.

If the blogger is interested in cooperation, explain the cooperation flow and request statistics (use the 'Interested' action). If the blogger is not interested in cooperation, politely ask why (use the 'Not interested' action and mark them as 'Negotiation'). If the blogger replied with all the necessary information, escalate for manual review and mark them as 'provided info'.

At any point, if the conversation doesn't fit the flow, escalate for manual review.

So, how does this AI agent work?

1. It receives a reply to your outreach campaign.
2. The agent analyzes the conversation.
3. If the blogger is interested, the agent explains the next steps and asks for their stats (by triggering the 'Interested' Quick Action).
4. If the blogger isn't interested, the agent will ask for feedback (by using the 'Not interested' action) and move them to the 'Negotiation' stage.
5. Once an interested blogger provides their stats, the agent flags the conversation for your review and moves them to the 'Provided info' stage.

IMPORTANT: Do not change the first and last sentences of the instructions! The first sentence gives the AI agent context for the conversation. The last sentence is a crucial safeguard that tells the agent to stop and notify you for a manual review if it encounters a situation not covered in its instructions, preventing it from going off-script.

Other examples can be found here.