Your dot can follow an assigned responsibility between conversations. A time or a supported event may trigger work; a connected source alone does not create a monitoring task.
Understand assigned ongoing work, schedules, events, and proactive research. Begin by asking what the result must prove. A short, sourced answer can be more valuable than a polished page of assumptions.
Define the task
What to prepare before you begin
Before you open another connection, assemble scope, trigger, time zone, end condition, review rules. Check whether those materials already answer the question you intend to ask.
A useful deliverable
A confirmed task and reporting rhythm. Require any exception or missing field to be called out rather than filled with a guess.
Worked situation
How this plays out in practice
"Tell me every Monday if a report changes" requires a schedule, source, definition of change, and a destination for the result. Notice how one changed detail alters the judgment. Keep that detail in the brief and inspect whether it survives into the final draft.
Confirm that a task or supported event trigger was actually saved. Name the stop condition and what the dot should do when the source is unavailable. Keep enough of the trail that a later reviewer can retrace the conclusion when the source changes.
A practical sequence
Run a bounded first pass
Open with scope, trigger, time zone, end condition, review rules and a sentence explaining how you will recognize a useful answer.
Define what to watch, what sources to read, when to report, what result to prepare, and when to stop. Ask the dot to confirm a saved schedule or event trigger. Require the answer to show its assumptions before it recommends a next step.
Check the current status, then enforce do not infer a schedule from a conversation. Repeating a task should not repeat a completed action.
Editorial judgment
Where a plausible answer can fail
A connected app by itself is not a watcher. Also distinguish read-only proactive research from a separately authorized task that can write. Ask what evidence would falsify the proposed answer. That question often exposes the missing piece.
Proactive research itself uses read-only tools. An assigned recurring task may perform separately authorized actions, so inspect Scheduled and app permissions. State the limitation in ordinary language so someone using the result does not mistake it for a verified fact.
Where to go next
Connect this result to the right follow-up
The Features & How Dots Work hub gives you the broader route and neighboring tasks. Return there when the present job has produced a result, rather than adding an unrelated responsibility to the same brief. A good handoff identifies what has been settled here and what belongs to the next task.
For a closely related outcome, open Dots Memory and Personalization. That guide focuses on know what your dot may remember and how to correct it. It may use some of the same context, but you should confirm the source and the decision point again. If your next question is about a different angle, Connect Your Local Computer to Dots is a better fit: understand what changes when you connect your own computer. A new deliverable should have its own date, owner, and acceptance check.
Before you reuse this result elsewhere, look at Dots Privacy, Memory and Permissions for the wider product or review boundary. Take forward the verified facts and leave behind any assumption that was specific to this example. If the source has changed since the draft was made, update the relevant claim first. The purpose of the link is to make the next step more precise, not to imply that every connected guide is needed for every reader.
Adapt this
Build your own task brief
Edit the bracketed information and any sentence that does not fit your account. This is a suggested workflow, not a promise that your dot has access to a particular app or feature.
Your review
Check before moving on
Tick what you have actually checked. Your progress stays on this device for this page and can be cleared at any time.
0 of 4 checked
Questions
Frequently asked questions
Where should I verify this feature?
Use the scenario on this page as a small test. Confirm that a task or supported event trigger was actually saved. Name the stop condition and what the dot should do when the source is unavailable. Keep a source and a date beside any detail that can change.
What information matters most for background work, recurring tasks and follow-ups?
Start with scope, trigger, time zone, end condition, review rules. Your dot can follow an assigned responsibility between conversations. A time or a supported event may trigger work; a connected source alone does not create a monitoring task. Give the exact source or account where a decision depends on it.
What changes when a connected app is involved?
Proactive research itself uses read-only tools. An assigned recurring task may perform separately authorized actions, so inspect Scheduled and app permissions. The relevant access, audience, and consequences determine what you should approve.
What would a useful result look like here?
A confirmed task and reporting rhythm. It should make assumptions visible and leave a trail to the source, especially for dates, prices, permissions, or changing product details.
What is the common failure in this situation?
A connected app by itself is not a watcher. Also distinguish read-only proactive research from a separately authorized task that can write. Review that issue in the actual output instead of treating a polished presentation as proof.
Where can I check the current details?
Follow the official source linked below and inspect your account where access matters. This page was revised in October 2026; availability, terms, and product behavior can change.
Source for current product details: official OpenAI documentation or announcement ↗. The worked situations and briefs on this independent site are editorial examples. Confirm current access and details in your account. Editorial policy.