Asana Agent

Lets an AI agent carry out Asana requests written in plain language. Describe what you want done (create tasks, update projects, add comments, search for information) and the agent works out the individual Asana operations needed.

What It Does

Reads the instructions in your prompt and works through Asana on your behalf, using up to the number of steps you allow. It can create tasks, update existing ones, add comments, and search for tasks, projects, or people, chaining multiple operations together to complete a request that would otherwise take several separate nodes.

When To Use It

Use this when a task is too open-ended or variable for a fixed sequence of Asana nodes, such as "create a task for each action item from this meeting" or "update all high-priority tasks in the Q1 project." For simple, predictable operations like creating one task or updating one field, a dedicated node such as Create Task or Update Task is more reliable and easier to audit.

Configuration

Configure the node with these settings:

Field	What it controls
Related Object Type	The kind of context object given to the agent: `meeting`, `calendarEvent`, `person`, or `company`. Defaults to `meeting`.
Related Object	The specific meeting, contact, or company to use as context. The agent can reference details from this object.
Agent Prompt	Your instructions for what the agent should do in Asana. Required.
Show Message	When enabled, your prompt is visible in the resulting conversation. Defaults to off.
Show Completion	When enabled, the agent's response is visible in the conversation. Defaults to on.
Model	The AI model used to run the agent. Only Claude models are supported here; if you pick an OpenAI model, it is automatically switched to Claude.
Max Steps	The maximum number of Asana operations the agent can perform in one run, from 1 to 20. Defaults to `20`. Raise it for more complex multi-step requests.
Chat Title	An optional title for the conversation this creates. If left blank, the AI generates one.

Outputs

The node passes these values downstream. Check the Outputs tab on the configured node to confirm exact paths.

Variable	Type	Description	Example
`conversation`	`object`	A reference to the conversation where the message was sent	`{{nodeId.conversation}}`
`conversation.id`	`string`		`{{nodeId.conversation.id}}`
`conversationLink`	`string`	A clickable link to the created conversation in AskElephant	`{{nodeId.conversationLink}}`
`aiCompletion`	`string`	The LLM completion that was sent to the conversation	`{{nodeId.aiCompletion}}`

Example Workflow

After a sales call, a workflow passes the meeting as context and prompts the agent to "create a task for each follow-up action item and assign it to the account owner." The agent creates the tasks in Asana and posts a summary to the conversation.

Create Task
Update Task
Find Project
Find User

Need More Help?

Reach the AskElephant support team by:

clicking the Support tab on the right side of your screen,
emailing [email protected],
or using @askelephant support in your dedicated Slack channel.