Asana + OpenAI Dots
Design an Asana briefing service
An architecture guide for OpenAI Dots users
Design an Asana task assistant with OpenAI models and Agent200. This OpenAI Dots guide explains a separate application and its read-only boundaries.
On this page
Overview
This guide describes an Asana briefing service you build with OpenAI models and Agent200. It is separate from connecting a plugin to an OpenAI dot. Your application decides when to run a briefing, authenticates its user and passes that user's context to Agent200.
The Agent200 SDK examples on this page are conceptual. Use the actual runtime tool definitions and supported client interfaces supplied to your application. No package installation command, parameter mapping or end-to-end runtime test is implied.
Product reference: OpenAI Dots documentation. For Asana task fields and optional field selection, see Asana’s task-read reference.
- Connector
- Asana
- Works with
- OpenAI Dots ยท Your own agent code
- Authentication
- Managed OAuth, per end user
- You need
- An Agent200 API key
- Tools
- 6 tools
- Model in examples
openai/gpt-5.6-sol
Before you start
- An Agent200 API key. Create one on the API keys page of the dashboard.
- Asana enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- An end user with a Asana account. They approve access once, on Asana's own page.
- A model for your agent. The examples use openai/gpt-5.6-sol, through the same Agent200 API key.
Connect Asana to OpenAI Dots
-
1
Step 1: Create your Agent200 API key
Create a key on the API keys page. Enable Asana and the read operations needed for this task in your project. Keep credentials out of chats and source control.
.envConceptual exampleStore the Agent200 API key as an environment variable # Keep the key out of your code, prompts and chats. export AGENT200_API_KEY="paste-your-key-here" -
2
Step 2: Define the task-reading contract
Select the existing Asana task-read operation from the tool definitions supplied by your runtime. Validate the selected task ID and map only documented inputs and outputs. Keep credentials on the server.
-
3
Step 3: Connect the end user's Asana account
Have the end user complete the Asana authorization flow. Use the same authenticated application user for connection and later requests. Confirm that the user can open the task selected for the first read.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Asana account, once. const connection = await agent200 .user("user_123") .connect("asana"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
4
Step 4: Build the read-only briefing flow
Use the selected task’s returned details to produce the briefing. Handle missing fields and refused calls explicitly. The following snippet is a conceptual illustration of the site’s Agent200 flow; adapt the implementation to your real runtime contract.
openai-dots-asana.jsConceptual exampleGuide: the framework's model runs the connector's tools // OpenAI Dots handles the request; Agent200 executes its Asana tool calls. const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", instructions: "Use Asana when the request needs it.", input: "Find the task I'm referring to and summarise its current status.", tools: ["asana"], }); console.log(result.output);
Test your connection
Run one request to check everything is wired up.
Ask
Prepare a read-only Asana briefing for the task the user selected. Include its owner, due date, completion state and description when returned, and mark unavailable information clearly. Do not update Asana.
What should come back
- The selected task is identified clearly.
- The answer uses only the task information returned, including owner, due date and completion state when available.
- Missing fields and access failures are reported without guessing; no Asana records are changed.
If authorization is requested, complete it with the intended Asana account. If a tool or field is unavailable, report it and check the actual tool definition. Workspace task search has separate premium access requirements.
Get your API key
Create a key in the Agent200 dashboard. It reaches Asana and every other connector enabled for your project.
Instructions for AI agents
Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect Asana to OpenAI Dots.
Goal: connect Asana to OpenAI Dots with Agent200. Guide: https://www.agent200.com/connectors/asana/framework/openai-dots/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Make sure Asana is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs. 3. Add the Agent200 SDK to the project and create a client with that key. 4. Give every request a stable id for the end user. Agent200 uses only that user's own connections. 5. Connect the user's Asana account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Asana. 6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "asana" in the tools. The model decides when a Asana tool is needed; Agent200 executes the call. 7. Check it works with this request: "Prepare a read-only Asana briefing for the task the user selected. Include its owner, due date, completion state and description when returned, and mark unavailable information clearly. Do not update Asana." What should come back: - The selected task is identified clearly. - The answer uses only the task information returned, including owner, due date and completion state when available. - Missing fields and access failures are reported without guessing; no Asana records are changed. 8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Asana, then retry. The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
The whole guide is also available as Markdown, for agents and LLMs: /connectors/asana/framework/openai-dots.md
Asana tools OpenAI Dots can call
-
Read a task
Readasana_get_taskRetrieve an Asana task's details, including its description, assignee, due date and completion status.
-
Search tasks
Readasana_search_tasksSearch workspace tasks by text and filters. Requires Asana premium search access.
-
List project tasks
Readasana_list_project_tasksList the tasks in a selected project, then read individual tasks for descriptions, ownership and deadlines.
-
List subtasks
Readasana_list_subtasksList the subtasks of a parent task so your agent can inspect the smaller work items behind it.
-
List projects
Readasana_list_projectsList projects in a workspace to find the project relevant to a request.
-
Read a project
Readasana_get_projectRead a project's name and description to understand its purpose and context.
No tool matches that search.
How it works
-
01
Your app sends the request
It calls Agent200 with the model, instructions, the input, the end user's id and the Asana tools.
-
02
The model picks a tool
The model decides whether a Asana tool is needed, and with which arguments.
-
03
Agent200 runs the call
It uses that user's own Asana connection, within the endpoints and scopes your project allows, and returns the result to the model.
-
04
Your app gets the result
Agent200 returns the completed result. Your app decides when the agent runs and what happens next.
Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's Asana account.
Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and Asana enforces what its API grants.
Troubleshooting
The task is missing or cannot be read
Confirm the task ID and that the connected Asana user can open it. An access error is not an empty task. Ask for the right task rather than guessing an ID or claiming a result.
The answer omits the owner or deadline
Check the fields actually returned by the tool. An omitted field does not prove a task is unassigned or has no due date. Report unavailable information explicitly.
Task search fails even though a task read works
Asana workspace task search requires premium eligibility and may lag recent changes. Use an identified accessible task for the first test. See Asana’s search requirements.
FAQ
Does this configure an OpenAI dot or schedule a task?
No. It is a conceptual application architecture, not a dot installation or scheduling procedure. A dot uses its own connected plugins and permissions. Your application must supply scheduling, user identity and delivery behavior if it needs them.
