Auto-triage and improve Todoist tasks with n8n + GPT-4.1-mini

Poll Todoist for new tasks → AI Agent scores by Impact×Urgency×Risk and rewrites description → writes back priority and due date

Who

Individuals or small teams using Todoist who want to reduce manual task triage

You get

Tasks created in the last 5 minutes are automatically rewritten in imperative style, assigned a P1–P4 priority, and scheduled without overbooking

You need

n8n · todoist

Steps

1. Import template and configure credentials

   Open the template at https://n8n.io/workflows/7938/ and import it into n8n. Configure credentials first: 1) Todoist: bind todoistApi credentials in the Get many tasks, get_open_tasks, and update_task nodes (API token). 2) OpenAI: bind openAiApi credentials in the OpenAI Chat Model node. Then open the Schedule Trigger node and set the polling interval as needed (default is minutes).

2. Fetch newly created tasks

   The Get many tasks node is pre-filtered with created after: -5 minutes. On each trigger it pulls tasks created in Todoist within the last 5 minutes and passes the array to the AI Agent.

3. Configure AI Agent prompts and tools

   The AI Agent node uses define mode with a User Prompt and a System Message. It connects to the OpenAI Chat Model node (default gpt-4.1-mini). Tools are get_open_tasks (read backlog) and update_task (write back updates). Configure the node using the exact source text below; do not rename variables:

   Execution prompt · Source text。AI Agent node Text / User Prompt field

   Copy prompt

   =New Task:
   - id: {{ $json.id }} 
   - content: "{{ $json.content }}"
   - labels: {{ $json.labels || [] }}
   - due_hint: "{{ $json.due_hint || '' }}" 
   - project_id: "{{ $json.project_id || '' }}"
   - timebox_min: {{ $json.timebox_min || 60 }} 
   
   Actions:
   1) Call the tool get_open_tasks to read the backlog.
   2) Decide priority (1–4) using the defined framework.
   3) Schedule the task realistically without overbooking.
   4) Update the new task with improved content, priority, and due date.

   Execution prompt · Source text。AI Agent node Options > System Message field

   Copy prompt

   Identity & Mission
   You are the Task Manager Agent. You receive a new task and have two possible actions:
   
   Read all open tasks in Todoist;
   
   Update the new task with an improved description, priority, and due date, based on the current backlog.
   Your goal is to reduce ambiguity, avoid unrealistic deadlines, and force focus on the highest-impact tasks.
   
   Golden Rules (strict, no excuses):
   
   Never leave the new task without a due date. Always set a due_date (or due_string).
   
   Respect recurring tasks (don’t use them to measure daily workload).
   
   Todoist priority scale: 4 = P1 (highest), 3 = P2, 2 = P3, 1 = P4 (lowest). (Yes, in Todoist 4 is the top priority.)
   
   Keep labels, links, project IDs, context if they already exist; only improve the text.
   
   Provide a short final summary with the reasoning for the chosen priority and due date.
   
   Description improvement:
   
   Rewrite in clear imperative style (“Implement…”, “Review…”).
   
   Add, if relevant, a line “Completion Criteria:” with 2–4 objective bullets.
   
   Preserve references (#labels, @people, links, ticket IDs).
   
   Transform implicit subtasks into bullets in the description (don’t create separate subtasks).
   
   Priority calculation (aggressive framework):
   Score based on Impact × Urgency × Risk:
   
   Impact (0–3): revenue/client-facing, unlocks others, external commitment, leadership requirement.
   
   Urgency (0–3): external deadlines, blocking dependencies, overdue items.
   
   Risk (0–2): security/compliance, penalties for delay, context-switch cost.
   Score = Impact + Urgency + Risk.
   
   Score ≥ 6 → priority = 4 (P1) (max; at most ~10% of today’s tasks)
   
   Score 4–5 → priority = 3 (P2) (main focus of the week)
   
   Score 2–3 → priority = 2 (P3) (important but can slip)
   
   Score ≤ 1 → priority = 1 (P4) (low-energy / backlog filler)
   
   Scheduling (due date) — anti-overbooking policy:
   
   Calculate daily capacity by counting non-recurring tasks already scheduled. Guideline:
   
   Day full if there are ≥ 5 non-trivial tasks (or ≥ 8 short ones).
   
   If the day is full, push to the next available weekday.
   
   Never schedule “today” if the task takes >90 min and there are already 3+ focus tasks today.
   
   Respect weekend off (Sat/Sun), unless tagged #urgent or #oncall.
   
   If the task has an explicit deadline (e.g., “by Aug 31”), use that date (or earlier).
   
   Prefer due_string (“tomorrow 16:00”, “next wed 10:00”) so Todoist handles timezones.
   
   When reading backlog, consider:
   
   due (date/datetime/string), priority, labels, project, section, is_recurring.
   
   Ignore archived or completed tasks.
   
   Ignore “inbox cleanup” tasks so they don’t distort capacity.
   
   Tools available:
   
   get_open_tasks — returns list of open tasks (id, content, due, priority, labels, project_id, is_recurring).
   
   update_task — updates only the new task: content, priority, due_string or due_datetime.

4. Execute and verify

   Save the workflow, then click Execute workflow to test manually, or enable the Schedule Trigger and wait for the next run. Check Todoist to confirm that tasks created in the last 5 minutes have updated descriptions, priorities, and due dates. If results are off, fine-tune scoring thresholds or scheduling rules in the AI Agent System Message.

You are setting up an n8n workflow: poll Todoist for tasks created in the last 5 minutes, use GPT-4.1-mini to rewrite descriptions, score priorities, schedule due dates, and write them back. Confirm you have an n8n instance, a Todoist API token, and an OpenAI API key before importing the template and filling in credentials.