# Natural language task management with Todoist and OpenAI: n8n workflow

> Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/natural-language-task-management-with-todoist-and-openai (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [AI assistants](https://millionrounds.com/workflows?category=AI+assistants#library)

# Natural language task management with Todoist and OpenAI

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 33 steps: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fnatural-language-task-management-with-todoist-and-openai)

**33 steps** Large: read it before trusting it with anything live

**0** Branches: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 2 Model 6 Service 25

The steps in the order they run, from what starts it.

- 1 **When Executed by Another Workflow** Execute Workflow trigger *Starts it*
- 2 **When chat message received** Chat trigger *Starts it*
- 3 **Call Todoist Agent** Tool Workflow *Model*
- 4 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 5 **Simple Memory** Memory Buffer Window *Model*
- 6 **OpenAI Chat Model1** Lm Chat Open Ai *Model*
- 7 **Get All Tasks** Todoist Tool *Service*
- 8 **Get a Task** Todoist Tool *Service*
- 9 **Create a Task** Todoist Tool *Service*
- 10 **Update a Task** Todoist Tool *Service*
- 11 **Mark Task as Done** Todoist Tool *Service*
- 12 **Reopen a Task** Todoist Tool *Service*
- 13 **Move a Task** Todoist Tool *Service*
- 14 **Get All Projects** Http Request Tool *Service*
- 15 **Get a Project** Http Request Tool *Service*
- 16 **Create a Project** Http Request Tool *Service*
- 17 **Update a Project** Http Request Tool *Service*
- 18 **Archive a Project** Http Request Tool *Service*
- 19 **Get Archived Projects** Http Request Tool *Service*
- 20 **Unarchive a Project** Http Request Tool *Service*
- 21 **Get All Sections** Http Request Tool *Service*
- 22 **Get a Section** Http Request Tool *Service*
- 23 **Create a Section** Http Request Tool *Service*
- 24 **Update a Section** Http Request Tool *Service*
- 25 **Delete a Section** Http Request Tool *Service*
- 26 **Get All Labels** Http Request Tool *Service*
- 27 **Get a Label** Http Request Tool *Service*
- 28 **Create a Label** Http Request Tool *Service*
- 29 **Update a Label** Http Request Tool *Service*
- 30 **Delete a Label** Http Request Tool *Service*
- 31 **Add a Comment** Http Request Tool *Service*
- 32 **Todoist Agent** Agent *Model*
- 33 **Orchestrator** Agent *Model*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 33
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 33 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 33 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fnatural-language-task-management-with-todoist-and-openai)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also ai assistants, with the same services where possible, closest in size first.

- [**Bitrix24 AI-Powered RAG Chatbot for Open Line Channels** 33 steps · calls a model · Qdrant](https://millionrounds.com/workflow/bitrix24-ai-powered-rag-chatbot-for-open-line-channels)
- [**Generate AI governance policy PDFs with OpenAI and SerpAPI** 33 steps · calls a model · Outlook](https://millionrounds.com/workflow/generate-ai-governance-policy-pdfs-with-openai-and-serpapi)
- [**Automate agile project setup with OpenAI and Jira** 32 steps · calls a model · Gmail, Jira](https://millionrounds.com/workflow/automate-agile-project-setup-with-openai-and-jira)
- [**Automated email classification & response system with Groq AI** 34 steps · calls a model · Email, Pinecone](https://millionrounds.com/workflow/automated-email-classification-and-response-system-with-groq)
- [**Remediate Kubernetes CrashLoopBackOff incidents with OpenAI** 32 steps · calls a model](https://millionrounds.com/workflow/remediate-kubernetes-crashloopbackoff-incidents-with-openai)
- [**Smart human takeover & auto pause AI-powered Facebook Messenger** 32 steps · calls a model · n8n data table](https://millionrounds.com/workflow/smart-human-takeover-and-auto-pause-ai-powered-facebook-mess)