Weekly summary · 2026-W40

ChatGPT experiments tracker › Summary archive

Dots autonomous agents and expanded ChatGPT logged-out limits

The configuration reveals instructions for the new Dots autonomous agents and removes the wallet plugin. ChatGPT now allows fifteen logged-out messages.

2026-W40 · 2026-09-28 → 2026-10-04

2375
feature gates
493
dynamic configs
884
layers
2026-11-19
last update
Powered by RESONEO
2

The summary

Generated every Sunday evening from the week's new entries.

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.

3

Summary archive

Every archived week, immutable, in French and English, on its own page.

Price alerts for shopping and new map interfaces on ChatGPT This week's data reveals the preparation of shopping price alerts, new interactive map hover cards, and dynamic layout updates for the Pages feature. 2026-W46 2026-11-09 → 2026-11-15 66 items with substance ChatGPT Business workspaces and new dashboard format for Pages OpenAI is preparing a new Business offering with ad credits for workspaces. The Pages feature also gains a dashboard format and direct-save options. 2026-W45 2026-11-02 → 2026-11-08 55 items with substance Retirement of custom GPTs and proactive ChatGPT voice mode The code reveals the planned retirement of custom GPTs in December. ChatGPT is also testing a proactive voice agent and new subscription tiers. 2026-W44 2026-10-26 → 2026-11-01 44 items with substance ChatGPT experiments summary 2026-W43 2026-W43 2026-10-19 → 2026-10-25 97 items with substance Launch of ChatGPT Sites and new background tracking agents The code reveals the rollout of ChatGPT Sites for web artifacts, the addition of background agents, and predictive ad preloading based on click rates. 2026-W42 2026-10-12 → 2026-10-18 33 items with substance ChatGPT tests computer control and deep research plugins Hidden configurations reveal new ChatGPT plugins for computer use and deep research. An internal payment system is also tested to replace Stripe. 2026-W41 2026-10-05 → 2026-10-11 33 items with substance Dots autonomous agents and expanded ChatGPT logged-out limits The configuration reveals instructions for the new Dots autonomous agents and removes the wallet plugin. ChatGPT now allows fifteen logged-out messages. 2026-W40 2026-09-28 → 2026-10-04 9 items with substance Pinned composer ads and background agent controls in ChatGPT ChatGPT tests pinned ads above the composer, frames silent background automations, and introduces watermark detection for images generated by Gemini. 2026-W39 2026-09-21 → 2026-09-27 37 items with substance ChatGPT overhauls connectors and introduces an ads manager OpenAI shifts ChatGPT connectors toward an advertising manager, tests a payment-free Plus trial, and prepares a delayed generation system via Kafka. 2026-W38 2026-09-14 → 2026-09-20 37 items with substance Custom models retirement date and local caching in ChatGPT This weekly summary covers new local search caching features, the addition of a Lowe's advertising agent, and a retirement date for custom models. 2026-W37 2026-09-07 → 2026-09-13 44 items with substance ChatGPT adds autonomous web browsing and artifact creation ChatGPT system instructions now include autonomous browser actions and artifact generation. The GPT-5.6 Luna model is also deployed for text editing. 2026-W34 2026-08-17 → 2026-08-23 42 items with substance Financial data for ChatGPT Work and hidden GPT-5.6 models The configuration reveals financial data access for workspaces, the hiding of recent GPT-5.6 models, and the addition of a Wayfair advertising agent. 2026-W33 2026-08-10 → 2026-08-16 56 items with substance Expedia business agents and local search testing in ChatGPT The code reveals dedicated business agents for Expedia and the integration of Yelp for local search. Rich text editing features are also in preparation. 2026-W32 2026-08-03 → 2026-08-09 43 items with substance ChatGPT tests a personalized ad agent and Google integrations The latest configuration data reveals a minimum viable product for personalized ads, new Google Workspace integrations, and writing style personalization. 2026-W31 2026-07-27 → 2026-08-02 55 items with substance ChatGPT exposes future models and integrates medical data Configuration files reveal unreleased models like GPT-5-pro and o4-mini. ChatGPT also integrates official healthcare databases and new ad tracking tools. 2026-W30 2026-07-20 → 2026-07-26 58 items with substance Upcoming ChatGPT Work interface and enterprise integrations This summary details the upcoming ChatGPT Work interface connected to enterprise tools, native document generation, and a global billing infrastructure. 2026-W29 2026-07-13 → 2026-07-19 9 items with substance

Other sources and studies

Nov 2026 QRewrite: what Google adds to your query before it searches, with a live test of the inflections, synonyms and translations added to each word, the 0 to 13 score Google gives each word for each page, and the 98 kinds of outputs QRewrite can attach to a query Nov 2026 What Google sees in an image: the two vocabularies of its vision models, Knowledge Graph entities and the dimensions and values of Google Shopping filters, then the record, the 86 filter boxes and the signals that rank each image Nov 2026 Google’s 300 ranking signals, and the fifty that apply to your page: the 305 sets Google Search records for each result and each query, the 48 that apply to a web page, 31 of which score it, the rankers in a row and the 34 already serving AI Overviews, AI Mode and Web Guide Nov 2026 How Google spots good publishers, even small ones, from the site section score, topic authority and citations Google attaches to every blue link, all the way to the SERP and into AI answers, to the “human voices” pipeline behind the hidden gems Nov 2026 What Google personalizes, from the SERP to AI Mode: three questions at every AI Mode query, 392 kinds of profile data including profiles written for the models, Gmail read by AI Mode and the confirmation email that writes a brand into its customer’s profile Nov 2026 Google Shopping, from the SERP to AI Mode: what a product must prove to be shown, then bought, from four catalog scores (two of them drawn from clicks) and 82 filters to the five sheets the AI model reads and the universal cart Nov 2026 Twiddlers: what still moves a result after ranking, from the fan-out search plan, a Bard filter and a relevance oracle to E-E-A-T expertise, topic authority, spam and DMCA, with 120 twiddlers Oct 2026 Knowledge Graph: how Google feeds it, maintains it and makes it grow, from the passport every fact carries to the 194 access requirements that name its suppliers and the 8,679 collections that decide which requests an entity can fill Oct 2026 AI Overviews and AI Mode: what Google’s AI reads before it answers, from 138 result types to Knowledge Graph facts that reach the answer with no URL, with 9 internal schemas to browse Oct 2026 How Google matches pages to search intent: Intent Brain measures twenty broad intents from clicks for every query, language and country, Orbit sorts every page into 86 categories, with 15 internal schemas to browse More stuffs...
RESONEO