Highlights of the week
The configuration changes observed this week align closely with the recent DevDay announcements, particularly regarding the backend implementation of persistent autonomous agents. The underlying instructions for the newly announced "Dots" agents are now visible in the automation configurations. Additionally, the wallet plugin that appeared in the previous week's data has already been removed from the hidden list, and OpenAI is significantly relaxing the engagement limits for unauthenticated users.
Focus by theme
Search and local optimization
The wallet plugin identifier, which was newly introduced in the hidden plugins list last week, has been completely removed from this week's configuration. It is uncertain whether this indicates that the internal test for a transactional or identity feature was abandoned, or if the plugin has simply been moved out of the hidden state for a different phase of deployment.
For unauthenticated users, the parameter enforcing a concise response style has been disabled. This suggests that OpenAI is testing the delivery of standard, full-length search and chat responses to logged-out users, moving away from the truncated formats previously used to limit compute costs or encourage sign-ups.
Web run and integrations
OpenAI is adjusting the engagement thresholds for users interacting with the platform without an account. The soft rate limit modal, which triggers a prompt after a certain number of interactions, has been increased from 7 to 15 messages. This allows for significantly longer conversation threads and deeper web execution tasks before the user is interrupted.
Retrieval and grounding
Following the DevDay announcement of "Dots" (always-on AI agents), the automation configurations have been updated with new, explicit prompt instructions. The system now directs the model to handle an "ongoing goal with a private plan" and instructs it to "use available structured context to understand their goals and prior progress." This reveals the grounding mechanics behind the new agents, showing how they retrieve structured historical data to maintain context and advance long-term tasks across different sessions.
The extensive JSON formatting instructions for skipping notifications, which were deployed last week to control autonomous agent behavior, remain active in the configuration. This confirms a continued technical focus on silently logging agent progress without unnecessarily alerting the user.
To monitor
The interface adjustments for right-to-left languages, which were noted last week for unauthenticated users, are still undergoing refinement. New parameters have been activated to display a large orb and hide subtitles specifically on the bidirectional landing page, indicating ongoing efforts to optimize the international logged-out experience.
A new parameter enabling "best for" labels has been activated in the user interface. This is likely a test to help users navigate the expanding ecosystem of models and subscriptions, directly following the introduction of the GPT-6.1 Sol model and the new Pro 500 tier.
Finally, a new layout element is being tested for image generation, with a flag enabling a dedicated images sidebar that appears immediately after a new chat is initiated.
