TL;DR: This Wrike AI agent automates request triage by reading incoming tasks, and evaluating urgency. Built completely via the new conversational builder, the AI agent applies your rules across two actions simultaneously: it sets the native Importance field (High, Normal, Low) and emails a summarized update with a direct task link straight to the project owner.
Hello Community! 👋
Today we are sharing a guide to set up an Intake Triage and Route Agent. If your team manages a shared intake folder or request queue, you know how much manual effort it takes to review every submission, judge its actual priority, and ensure the right team is looped in.
Below, you will find the exact chat prompt to feed the Wrike AI Conversational Builder, the final settings configuration, and a breakdown of how it executes once it is live in your workspace ✔️
Agent Goal / Use Case
Standard automation rules apply the exact same static logic to every new task. They cannot read a messy description, evaluate actual urgency, or intelligently determine if a request belongs to Production, Marketing, or Operations.
By simply describing your routing logic to the new conversational builder, you can build a single agent that handles content analysis, judgment, and routing all at once.
This setup gives you:
- Native Urgency Mapping: The agent translates text signals straight into Wrike's native Importance field.
- Direct Notifications: Task owners receive an immediate, contextual email overview with a link back to the work item.
Built Entirely via Chat: The AI Conversational Builder 💬
💡 The Conversational Shift: You no longer have to manually piece together form elements, dropdown menus, or logic selectors. The prompt below is all it takes. The conversational builder interprets this natural text, structures the backend rules, and deploys the agent instantly.
Open up the Conversational Builder and paste the text block below to build this agent entirely through chat:
Hey! I want to build a triage agent for new requests.
When to run: > Whenever a new task is created in 'Intake Projects' and its 'Request Type' custom field is set to 'New'.
The Rules:
I want you to read the task details and figure out two things:
Priority: Pick High, Normal, or Low based on any deadlines or urgent keywords you find.
Assigned Team & Email: Send an email to the task owner with a short request summary and a direct link back to the Wrike task. In the email, clearly inform them which team the request has been routed to based on these rules:
-Production (if the content relates to manufacturing, design, or physical outputs)
-Marketing (if it relates to campaigns, branding, or social media)
-Operations (if it relates to logistics, facilities, or internal processes)
What to do:
-Set the native Wrike Importance field based on the priority you chose.
-Send an email to the task owner. In the email, include a quick summary of the request, name the assigned team, and provide a direct link back to the Wrike task.
The builder initiates the conversation and will ask clarifying questions or present options as you go. You simply chat back and forth with the builder to create and refine your agent.
Final Agent Settings ⚙️
Once the AI Conversational Builder processes your chat, it generates a structured configuration for your review. Take a look, tell the builder if you need to modify anything, and then click "Create."
How It Works After It Is Built and Appointed 🚀
Once you review the chat output, click create, and appoint the agent to your Intake Projects folder, the workflow runs entirely behind the scenes:
1. The Trigger Phase
A request submitter fills out an intake form or creates a new task in the folder. As long as the custom dropdown field Request Type is marked as New, the agent instantly wakes up.
2. Parallel Processing
The agent reads the task name, description, and custom fields, evaluating them against the master instructions provided during the chat build. Because the builder optimizes action execution, the two actions process concurrently using the same analytical baseline:
- The Priority Assessment: The agent looks for keywords like ASAP, broken, launching tomorrow, or explicit calendar dates. It maps its findings directly to the native Importance field.
- Identifying the Team: It scans the context to figure out the nature of the work. If it spots text about a social media asset, it marks the team as Marketing. If it talks about warehouse logistics, it selects Operations, and sends this information in the email.
3. Execution and Notification
The field updates are logged automatically in the Wrike task activity stream. At the exact same moment, an email is constructed and dispatched to the task owner. The email provides a clean, synthesized summary of the inbound request, clearly states the assigned team, and appends a functional link back to the Wrike task for rapid action.
Tips and Customization
- Refine Rules via Chat: If the agent misroutes a request, you don't need to dive into complex form menus to fix it. Simply open the conversational builder, pull up the agent, and say it naturally: "Update the routing rules so that any text mentioning trade shows goes to Marketing instead of Operations."
- Connect a Shared Inbox: For Action 2, you can link a team mailbox (like intake-triage@yourcompany.com) during the email account connection phase so notifications come from a centralized system rather than an individual person's user account.
- Monitor with the Grouped Log: Open the newly updated agent log to view runs grouped by session. You can see the exact text the agent parsed and the exact rationale it used to update the Importance field and draft the email, all in one neat timeline view.
- Swap Email for Slack or Teams: If your team prefers chat notifications over email, you can tell the builder to send the routed summary to a specific Slack or Microsoft Teams channel instead.
Let’s hear how your team handles this today!
- What is the closest thing your team does to sort incoming requests right now?
- How does building via the new Conversational Chat compare to the old method of hand-mapping forms and triggers?
- If you could add a third action to this agent using chat, what would it be? (e.g., Auto-populating a specialized project blueprint based on the team selected?)
Do let us know in the comments below! 🙌
