OpenAI adds Scheduled page to ChatGPT for managing tasks
TL;DR
OpenAI adds a Scheduled page to the ChatGPT sidebar for viewing, pausing, editing, or deleting tasks. The update retires Pulse and sends alerts only when research results change.
What changed
OpenAI added a Scheduled page to the ChatGPT sidebar that collects all active tasks for viewing pausing editing or deletion. Research tasks now scan the web and connected apps then send alerts only on detected changes. The prior Pulse feature has been retired.
Why it matters
Basic Users gain simpler oversight of recurring research without scattered notifications. Vibe Builders can maintain steady monitoring flows that trigger only on real updates. Developers see clearer paths to layer scheduling into their own automations compared to Microsoft Copilot which offers no equivalent single page for task management.
What to watch for
Check how the new controls perform against Claude Projects for similar recurring queries. Open the ChatGPT sidebar after the next update and test creating a research task to verify alert behavior on sample data changes.
Who this matters for
- Vibe Builders: Use the new Scheduled page to manage monitoring flows that trigger alerts only on data updates.
Harsh’s take
OpenAI is finally cleaning up its UI by centralizing task management. The transition from the messy Pulse feature to a dedicated Scheduled sidebar page shows a shift toward reliable agentic behavior. This is a direct hit to Microsoft Copilot, which remains cluttered and lacks a unified view for recurring tasks.
For operators, the real value is the noise reduction. Research tasks that only ping you when web or app data actually changes move ChatGPT from a chatbot to a passive monitor. It is a functional upgrade for anyone running competitive intelligence or price tracking.
This update proves that utility beats chat interfaces every time.
by Harsh Desai
More AI news
- Daily RoundupMuse Spark 1.2 on Vercel, v0 API launch, and fresh agent tools for builders
Vercel rolled out Muse Spark 1.2, expanded Sandbox limits, and the v0 API while Google shifted DeepMind leadership and new models appeared on Hugging Face and Fal.
- Daily RoundupDeepSeek V4 Flash 90% off, NVIDIA Alpamayo 2 for AVs, and agent tools shipping today
Vendors pushed model discounts, autonomous vehicle models, faster deploys, and browser-equipped agents while open models and cloud deals advanced across the board.
- Daily RoundupQwen 3.8 debut, lipsync model on Replicate, and agent tools for daily builds
Vendors released new models and infrastructure updates while builders gained fresh agent and coding tools across Replicate, Hugging Face, and Product Hunt on 3 August.